SlideTeam, profile picture
Uploaded bySlideTeam
PDF, PPTX838 views

Reinforcement Learning In AI Powerpoint Presentation Slide Templates Complete Deck

The document provides an overview of artificial intelligence (AI), machine learning (ML), and deep learning (DL), covering definitions, processes, algorithms, and applications in various fields. It details the concepts of supervised, unsupervised, and reinforcement learning, comparing traditional programming with machine learning approaches. Additionally, it discusses the importance of AI and its trends, particularly in the context of advancements seen in 2020.

Embed presentation

Download as PDF, PPTX
Reinforcement Learning in AI PowerPoint Presentation Slide Templates Y o u r C o m p a n y N a m e
2 Table of Content Machine Learning • What is Machine Learning? • 7 Steps of Machine learning • Machine Learning vs. Traditional Programming • How does machine learning work? • Machine learning Algorithms • Machine learning use cases • How to choose Machine Learning Algorithm • Why to use decision tree algorithm learning • Challenges and Limitations of Machine learning • Application of Machine learning • Why is machine learning important? Deep Learning • What is Deep Learning? • Deep learning Process • Classification of Neural Networks • Types of Deep Learning Networks • Feed-forward neural networks • Recurrent neural networks (RNNs) • Convolutional neural networks (CNN) • Reinforcement Learning • Examples of deep learning applications • Why is Deep Learning Important? • Limitations of deep learning Difference between AI vs ML vs DL • What is AI? • What is ML? • What is Deep Learning? • Machine Learning Process • Deep Learning Process • Difference between Machine Learning and Deep Learning • Which is better to start AI,ML or Deep learning Introduction • What is AI? • Introduction to AI Levels? • Types of Artificial Intelligence • AI VS machine learning vs deep learning • Where is AI used? • AI use cases • Why is AI booming now? • AI trend in 2020
3 Table of Content Unsupervised Machine Learning • What is Unsupervised Learning? • How Unsupervised Machine Learning works • Types of Unsupervised Learning • Disadvantages of Unsupervised Learning Reinforcement Learning • What is reinforcement learning? • How reinforcement learning works • Types of reinforcement learning • Advantage of reinforcement learning • Disadvantage of reinforcement learning Expert System in Artificial Intelligence • What is an Expert System? • Examples of Expert Systems • Characteristic of Expert System • Components of the expert system • Conventional System vs. Expert system • Human expert vs. expert system • Benefits of expert systems • Limitations of the expert system • Applications of expert systems Back Propagation Neural Network in AI • Back Propagation Neural Network in AI • What is Artificial Neural Networks? • What is Backpropagation? • Why We Need Backpropagation? • What is a Feed Forward Network? • Types of Backpropagation Networks • Best practice Backpropagation Supervised Machine Learning • Types of Machine Learning • What is Supervised Machine Learning? • How Supervised Learning Works • Types of Supervised Machine Learning Algorithms • Supervised vs. Unsupervised Machine learning techniques • Advantages of Supervised Learning • Disadvantages of Supervised Learning
4 Introduction 01 • What is AI? • Introduction to AI Levels? • Types of Artificial Intelligence • AI VS machine learning vs deep learning • Where is AI used? • AI use cases • Why is AI booming now? • AI trend in 2020
5 Transforming the Nature of Work, Learning, and Learning to Work Artificial intelligence (AI) is a popular branch of computer science that concerns with building “intelligent” smart machines capable of performing intelligent tasks. With rapid advancements in deep learning and machine learning, the tech industry is transforming radically. Artificial Intelligence Deep Learning Machine Learning This slide is 100% editable. Adapt it to your needs and capture your audience's attention. Artificial Intelligence
Introduction to AI Levels? 6 Artificial Narrow Intelligence Artificial General Intelligence Artificial Super Intelligence Types of Artificial Intelligence This slide is 100% editable. Adapt it to your needs and capture your audience's attention.
Types of Artificial Intelligence 7 This slide is 100% editable. Adapt it to your needs and capture your audience's attention. Machine Learning Artificial Intelligence Deep Learning
Artificial Intelligence 8 2020 2019 2018 2020 2019 2018 AI 2016 2017 2018 2019 2020 AI 65% 35% Artificial intelligence (AI) is a popular branch of computer science that concerns with building “intelligent” smart machines capable of performing intelligent tasks. With rapid advancements in deep learning and machine learning, the tech industry is transforming radically. This slide is 100% editable. Adapt it to your needs and capture your audience's attention This slide is 100% editable. Adapt it to your needs and capture your audience's attention This slide is 100% editable. Adapt it to your needs and capture your audience's attention This slide is 100% editable. Adapt it to your needs and capture your audience's attention This slide is 100% editable. Adapt it to your needs and capture your audience's attention This slide is 100% editable. Adapt it to your needs and capture your audience's attention This slide is 100% editable. Adapt it to your needs and capture your audience's attention This slide is 100% editable. Adapt it to your needs and capture your audience's attention This slide is 100% editable. Adapt it to your needs and capture your audience's attention
Machine Learning 9 Machine learning is a type of AI that enables machines to learn from data and deliver predictive models. The machine learning is not dependent on any explicit programming but the data fed into it. It is a complicated process. Based on the data you feed into machine learning algorithm and the training given to it, an output is delivered. A predictive algorithm will create a predictive model. This slide is 100% editable. Adapt it to your needs and capture your audience's attention.
Deep Learning 10 This slide is 100% editable. Adapt it to your needs and capture your audience's attention. Deep Learning is a subfield of machine learning that is concerned with algorithms inspired by the brain's structure A computer model can be taught using Deep Learning to run classification actions using pictures, texts or sounds as input functions known as artificial neural networks &
AI VS Machine Learning VS Deep Learning 11 • Machine Learning originated around 1960s • Machine learning is the practice of getting machines to make decisions without being programmed • Machine learning is a subset of AI & Data Science • Aim is to make machines learn through data so that they can solve problems Machine Learning • Deep Learning originated around 1970s • Deep Learning is the process of using artificial neural networks to solve complex problems • Deep Learning is a subset of Machine Learning, AI & Data Science • Aim is to build neural networks that au6tonetically discover patterns for feature detection Deep Learning • Artificial Intelligence originated around 1950s • AI represents simulate intelligence in machines • AI is a subset of data science • Aim is to build machines which are capable of thinking like humans Artificial Intelligence This slide is 100% editable. Adapt it to your needs and capture your audience's attention.
Where is AI used? 12 Customer Experience Supply Chain Human Resources Knowledge Creation Research & Development Fraud Detection Real-time Operations Management Customer Services Risk Management & Analytics Customer Insight Pricing & Promotion Predictive Analytics This slide is 100% editable. Adapt it to your needs and capture your audience's attention.
AI Usecase in HealthCare 13 AI and Robotics Research Keeping Well Early Detection Diagnosis Decision Making Treatment End of Life Care Training This slide is 100% editable. Adapt it to your needs and capture your audience's attention.
AI Use Cases in Human Resource 14 LEARNING • Curated Training • Skill Development RECRUITING • Dynamic Career Sites • Smart Sourcing ENGAGEMENT • HR Chatbot • Engagement Surveys ONBOARDING • Automated Messages • Curated Videos Employee Life Cycle This slide is 100% editable. Adapt it to your needs and capture your audience's attention.
AI in Banking for Fraud Detection 15 Configuration Workstation Expert Rules Execute Rules Definition Neural Network Engine Scoring Engine Authorization System Case Creation Module Case Management Database Expert Authorization Response Module Expert Rules Base Cardholder Profiles Postings Payment System Nonmonetary System Analyst Workstation Auth Request Case Creation Rules Execute Payment and Non-Monetary Transactions Auth Recommendation Auth Request & Score Transaction & Score Case Information 08 01 02 05 06 07 04 03 This slide is 100% editable. Adapt it to your needs and capture your audience's attention.
AI in Supply Chain 16 Logistics Service Procurement Manufacturing Customers Pervasive Visibility Proactive Replenishment Predictive Maintenance IIOT – Securely Provisionally People, System and Things Digital Ecosystem Data Lake Secure Access Via Identity Management for Transient Users Secure Device Maintenance Unified Messaging Actionable Insights Ecosystem Integration Structured & Unstructured Information Regulatory Data B2B Transaction Data Inventory Data Multimedia Data Sensor Data Logistics Data Trading Partner Data Social Media Data This slide is 100% editable. Adapt it to your needs and capture your audience's attention.
Ai Chatbots in Healthcare 17 Search Engine Users learn to search for information Social Platforms Like Facebook connect users online Smartphones Bring the internet online App Eco-system Lets users download and use apps easily Messenger Apps Lets users chat anywhere, anytime Artificial Intelligence Self Learning machines becomes smarter the more they are used Healthbots Bring all of the above together for healthcare use cases This slide is 100% editable. Adapt it to your needs and capture your audience's attention.
Why is AI booming now? 18 100% 92% 84% 45% 54% United States China India Germany Israel 22% 24% 27% 36% 37% 51% 60% 60% 66% 71% 0 20 40 60 80 100 Fleet Mobile Expediting Transactions Production Floor Systems Logistics & Supply Chain Monitoring Through External Devices/Systems Operational Environment HR/Workforce Management Security/Fraud Customer Relation/Interaction (i.e., chatbots) External Communication 8,097 7,540 7,336 4,680 4,201 3,714 3,655 3,564 3,169 0 2,000 4,000 6,000 8,000 Static Image Recognition, Classification and Tagging Algorithm Trading Strategy Performance Management Efficient, Scalable Processing of Patient Data Predictive Maintenance Object Identification, detection, classification, tracking Text Query of Images Automated Geophysical Feature Detection Content Distribution on Social Media Object detection & classification, avoidance, navigation Global AI Revenue Forecast by 2025, Ranked by Use Case in millions US Dollar Penetration of Artificial Intelligence Skills, by Country Organizations deploying AI, by Functional Areas
10 AI Trend in 2020 19 AI Trends” “2020 Robotic Process Automation AI will make Healthcare more Accurate Data Modeling will move to the Edge AI will Come for B2B Ai-powered Chatbots AI In Retail Aerospace and Flight Operations Controlled by AI AI Mediated Media and Entertainment Advanced Cybersecurity Automated Business Process This slide is 100% editable. Adapt it to your needs and capture your audience's attention.
20 • What is Machine Learning? • 7 Steps of Machine learning • Machine Learning vs. Traditional Programming • How does machine learning work? • Machine learning Algorithms • Machine learning use cases • How to choose Machine Learning Algorithm • Why to use decision tree algorithm learning • Challenges and Limitations of Machine learning • Application of Machine learning • Why is machine learning important? Machine Learning 02
Machine Learning 21 Machine Learning is the result of General AI that involves developing machines that can deliver results better than humans Input Data: Feed Learner Various Data Output Data: Present Rules “Learning” Machine Learning System Traditional Programming Data (Input) Program Output Data (Input) Output Machine Learning Program This slide is 100% editable. Adapt it to your needs and capture your audience's attention.
7 Steps of Machine Learning 22 This slide is 100% editable. Adapt it to your needs and capture your audience's attention. Gathering Data Preparing that Data Choosing a Model Training Evaluation Hyperparameter Tuning Prediction
Machine Learning vs. Traditional Programming 23 Machine Learning Learning Model Sample Data Expected Result Computer Prediction Result New Data Model Computer Prediction Result Computer Data Handcrafted Model Traditional Modelling This slide is 100% editable. Adapt it to your needs and capture your audience's attention.
How does Machine Learning Work? 24 This slide is 100% editable. Adapt it to your needs and capture your audience's attention. Identify, the problem to be solved and create a clear objective. Define Objectives Preparing data is a crucial step and involves building workflows to clean, match and blend the data. Prepare Data Data is fed as input and the algorithm configured with the required parameters. A percent of the data can be utilized to train the model. Train Model Publish the prepared experiment as a web service, so applications can use the model. Integrate Model Collect data from hospitals, health insurance companies, social service agencies, police and fire dept. Collect Data Depend on the problem to be solved and the type of data an appropriate algorithm will be chosen. Select Algorithm The remaining data is utilized to test the model, for accuracy. Depending on the results, improvements, can be performed in the “Train model’ and/or “Select Algorithm” phases, iteratively. Test Model
Machine Learning Algorithms 25 This slide is 100% editable. Adapt it to your needs and capture your audience's attention. • Linear • Polynomial • KNN • Trees • Logistic Regression • Naïve-Bayes • SVM • SVD • PCA • K-means • Apriori • FP-Growth Reinforcement Machine Learning Regression Clustering Decision Tree Classification Association Anlaysis Supervised Unsupervised Random Forest Hidden Markov Model Continuous Categorical
Machine Learning Use Cases 26 This slide is 100% editable. Adapt it to your needs and capture your audience's attention. Energy Feedstock & Utilities • Power Usage Analytics • Seismic Data Processing • Your Text Here • Smart Grid Management • Energy Demand & Supply Optimization Financial Services • Risk Analytics & Regulation • Customer Segmentation • Your Text Here • Credit Worthiness Evaluation Travel & Hospitality • Aircraft Scheduling • Dynamic Pricing • Your Text Here • Traffic Patterns & Congestion Management Manufacturing • Predictive Maintenance or Condition Monitoring • Your Text Here • Demand Forecasting • Process Optimization • Telematics Retail • Predictive Inventory Planning • Recommendation Engines • Your Text Here • Customer ROI & Lifetime Value Healthcare & Life Sciences • Alerts & Diagnostics from Real-time Patient Data • Your Text Here • Predictive Health Management • Healthcare Provider Sentiment Analysis
How to Choose Machine Learning Algorithm 27 This slide is 100% editable. Adapt it to your needs and capture your audience's attention. What do you want to do with your Data? Additional Requirements Accuracy Linearity Number of Parameters Training Time Number of Features How to Select Machine Learning Algorithms Algorithm Cheat Sheet
Why use Decision Tree Machine Learning Algorithm? 28 This slide is 100% editable. Adapt it to your needs and capture your audience's attention. Decision Trees To Classify Responsible Variable has only 2 Categories Response Variable has Multiple Categories Use Standard Classification here Use c4.5 Implementation Non-linear Relationship between Predictors & Response Linear Relationship between Predictors & Response Use c4.5 Implementation Use Standard Regression Tree To Predict Responsible variable is Continuous
Challenges and Limitations of Machine learning 29 This slide is 100% editable. Adapt it to your needs and capture your audience's attention. Advantages Disadvantages Easily Identifies Trends and Patterns No Human Intervention needed Handling multi-dimensional & multi-variety Data Continuous Improvement Wide Applications Data Acquisition High error- Susceptibility Time and Resources Interpretation Results
Application of Machine Learning 30 This slide is 100% editable. Adapt it to your needs and capture your audience's attention. Automatic Language Translation Medical Diagnosis Stock Market Trading Online Fraud Detection Virtual Personal Assistant Email Spam and Malware Filtering Self Driving Cars Product Recommendations Traffic Prediction Speech Recognition Image Recognition
Why is Machine Learning Important? 31 This slide is 100% editable. Adapt it to your needs and capture your audience's attention. Training Data • Normalization • Dimension Reduction • Image Processing, etc. Pre-Processing • Supervised • Unsupervised • Minimization, etc. Learning • Precision/recall • Over fitting • Test/cross Validation data, etc. Error Analysis Phase 2: Prediction Phase 1 : Learning Model New Data Predicted Data Prediction
32 • What is Deep Learning? • Deep learning Process • Classification of Neural Networks • Types of Deep Learning Networks • Feed-forward neural networks • Recurrent neural networks (RNNs) • Convolutional neural networks (CNN) • Reinforcement Learning • Examples of deep learning applications • Why is Deep Learning Important? • Limitations of deep learning Deep Learning 03
What is Deep Learning? 33 Input Feature Extraction + Classification Output Car Not Car What is Deep Learning? Deep Learning is a subfield of machine learning that is concerned with algorithms inspired by the brain's structure and functions known as artificial neural networks. A computer model can be taught using Deep Learning to run classification actions using pictures, texts or sounds as input. This slide is 100% editable. Adapt it to your needs and capture your audience's attention.
Deep Learning Process 34 This slide is 100% editable. Adapt it to your needs and capture your audience's attention. Understand the Problem Identify Data Select Deep Learning Algorithms Training the Model Test the Model
Classification of Neural Networks 35 This slide is 100% editable. Adapt it to your needs and capture your audience's attention. x1 x2 xn v11 v12 vpn w11 w22 wmp ym y2 y1 1 2 m V1n w1p Input Layer Hidden Layer Output Layer 1 2 p
Types of Deep Learning Networks 36 Supervised Artificial Neural Networks Used for Regression & Classification Convolutional Neural Networks Used for Computer Vision Recurrent Neutral Networks Used for Time Series Analysis Unsupervised Self-Organizing Maps Used for Feature Detection Deep Boltzmann Machines Used for Recommendation Systems AutoEncoders Used for Recommendation Systems Deep Learning Models • Artificial Neural Networks (ANN) • Convolutional Neural Networks (CNN) • Recurrent Neural Networks (RNN) Supervised • Self Organizing Maps (SOM) • Boltzmann Machines (BM) • AutoEncoders (AE) Unsupervised This slide is 100% editable. Adapt it to your needs and capture your audience's attention.
Feed-forward Neural Networks 37 This slide is 100% editable. Adapt it to your needs and capture your audience's attention. Input Layer Hidden Layer Output Layer Variable- #1 Variable- #2 Variable- #3 Variable- # 4 Output
Recurrent Neural Networks (RNNs) 38 This slide is 100% editable. Adapt it to your needs and capture your audience's attention. Input Layer Recurrent Network Output Layer Hidden Layers x1 x2 y
Convolutional Neural Networks (CNN) 39 Take Car = A1 Truck = B1 VAN = C1 Bicycle = D1 Rest all be Same This slide is 100% editable. Adapt it to your needs and capture your audience's attention.
Reinforcement Learning 40 Reinforcement Learning uses rewards and punishment to train computing models to perform a sequence of selections. Here computing faces a game-like scenario where it employs trial and error to answer. Based on the action it performs, computing gets either rewards or penalties. Its goal is to maximize the rewards. Action State, Reward Agent Environment Exploration Policy Filters Algorithm Neural Networks Memory This slide is 100% editable. Adapt it to your needs and capture your audience's attention.
Examples of Deep Learning Applications 41 Image Recognition Portfolio Management & Prediction of Stock Price Movements Speech Recognition Natural Language Processing Drug Discovery & Better Diagnostics of Diseases in Healthcare Robots and Self - Driving Cars This slide is 100% editable. Adapt it to your needs and capture your audience's attention.
Why is Deep Learning Important? 42 Deep Learning Other Learning Algorithms Performance Data This slide is 100% editable. Adapt it to your needs and capture your audience's attention.
Limitations of Deep Learning 43 Interpretability Statistical Reasoning Amount of Data Limitations of Deep Learning This slide is 100% editable. Adapt it to your needs and capture your audience's attention.
44 • What is AI? • What is ML? • What is Deep Learning? • Machine Learning Process • Deep Learning Process • Difference between Machine Learning and Deep Learning • Which is better to start AI,ML or Deep learning Difference between AI vs ML vs DL 04
Difference between AI vs ML vs DL 45 Engineering of making intelligent machines and programs Artificial Intelligence Ability to learn without being explicitly programmed Machine Learning Learning based on deep neural network Deep Learning This slide is 100% editable. Adapt it to your needs and capture your audience's attention.
What is AI? 46 Artificial intelligence (AI) is a popular branch of computer science that concerns with building “intelligent” smart machines capable of performing intelligent tasks. With rapid advancements in deep learning and machine learning, the tech industry is transforming radically. This slide is 100% editable. Adapt it to your needs and capture your audience's attention.
What is ML? 47 This slide is 100% editable. Adapt it to your needs and capture your audience's attention. Machine Learning is a type of AI that enables machines to learn from data and deliver predictive models. The machine learning is not dependent on any explicit programming but the data fed into it. It is a complicated process. Based on the data you feed into machine learning algorithm and the training given to it, an output is delivered. A predictive algorithm will create a predictive model. Learns Predicts Improves Machine Learning Ordinary System With AI Introduction to Machine learning
What is Deep Learning? 48 This slide is 100% editable. Adapt it to your needs and capture your audience's attention. Deep Learning Artificial intelligence (AI) is a popular branch of computer science that concerns with building “intelligent” smart machines capable of performing intelligent tasks. With rapid advancements in deep learning and machine learning, the tech industry is transforming radically.
Machine Learning Process 49 Data Gathering Building Model & Finalising Data Transformation into Predictions Data Cleaning Selecting Right Algorithms Modelling Candidate & Final Visualisation Predictions & Strategy Data Raw & Training Data This slide is 100% editable. Adapt it to your needs and capture your audience's attention.
Deep Learning Process 50 This slide is 100% editable. Adapt it to your needs and capture your audience's attention. Understand the Problem Identify Data Select Deep Learning Algorithm Training the Model Test the Model
Difference between Machine Learning and Deep Learning 51 Feature Extraction Classification Output Car Not Car Input Machine Learning Deep Learning Feature Extraction + Classification Car Not Car Output Input This slide is 100% editable. Adapt it to your needs and capture your audience's attention.
Which is better to start AI,ML or DL? 52 Subset of AI Techniques which use Statistical Methods to Enable Machines to Improve with Experiences. Machine Learning Any Technique which enables computers to mimic human behavior. Artificial Intelligence Subset of ML which make the Computation of Multi- layer Neural Networks Feasible. Deep Learning This slide is 100% editable. Adapt it to your needs and capture your audience's attention.
53 Supervised Machine Learning 05 • Types of Machine Learning • What is Supervised Machine Learning? • How Supervised Learning Works • Types of Supervised Machine Learning Algorithms • Supervised vs. Unsupervised Machine learning techniques • Advantages of Supervised Learning: • Disadvantages of Supervised Learning
Types of Machine Learning 54 This slide is 100% editable. Adapt it to your needs and capture your audience's attention. Supervised Learning Unsupervised Learning Reinforcement Learning Makes Machine Learn Explicitly Data with Clearly defined Output is given Direct feedback is given Predicts outcome/future Resolves Classification and Regression Problems Training Inputs Outputs Machine Understands the data (Identifies Patterns/ Structures) Evaluation is Qualitative or Indirect Does not Predict/Find anything Specific Inputs Outputs An approach to AI Reward Based Learning Learning form +ve & +ve Reinforcement Machine Learns how to act in a Certain Environment To Maximize Rewards Rewards Inputs Outputs
What is Supervised Machine Learning? 55 Supervised Learning This slide is 100% editable. Adapt it to your needs and capture your audience's attention. Input Raw Data Processing Output Algorithm Training Data set Desired Output Supervisor
How Supervised Machine Learning works 56 Provide the Machine Learning Algorithm Categorized or “labeled” Input and Output Data from to Learn Feed the Machine New, Unlabeled Information to See if it Tags New Data Appropriately. If not, Continue Refining the Algorithm Step 1 Step 2 Types of Problems to Which it’s Suited Machine Label “Group 1” Machine Group 1 Group 2 Classification Sorting Items into Categories Regression Identifying Real Values (Dollars, Weight, etc.)
Types of Supervised Machine Learning Algorithms 57 This slide is 100% editable. Adapt it to your needs and capture your audience's attention. Classification • Fraud Detection • Email Spam Detection • Diagnostics • Image Classification Regression • Risk Assessment • Score Prediction Supervised Learning
Supervised vs. Unsupervised Machine Learning Techniques 58 This slide is 100% editable. Adapt it to your needs and capture your audience's attention. Supervised Learning • Classification • Regression Input & Output Data Predictions & Predictive Models Unsupervised Learning • Clustering • Association Input Data Patterns / Structure Discovery vs
Advantages of Supervised Learning 59 Advantages It allows you to be very specific about the definition of the labels. In other words, you'll train the algorithm to differentiate different classes where you'll set a perfect decision boundary. You are ready to determine the amount of classes you would like to possess. The input file is extremely documented and is labeled. The results produced by the supervised method are more accurate and reliable as compared to the results produced by the unsupervised techniques of machine learning. this is often mainly because the input file within the supervised algorithm is documented and labeled. this is often a key difference between supervised and unsupervised learning. The answers within the analysis and therefore the output of your algorithm are likely to be known thanks to that each one the classes used are known. This slide is 100% editable. Adapt it to your needs and capture your audience's attention.
Disadvantages of Supervised Learning 60 Disadvantages • Supervised learning are often a posh method as compared with the unsupervised method. The key reason is that you simply need to understand alright and label the inputs in supervised learning. • It doesn’t happen in real time while the unsupervised learning is about the important time. this is often also a serious difference between supervised and unsupervised learning. Supervised machine learning uses of-line analysis. • It is needed tons of computation time for training. • If you've got a dynamic big and growing data, you're unsure of the labels to predefine the principles. this will be a true challenge. This slide is 100% editable. Adapt it to your needs and capture your audience's attention.
61 • What is Unsupervised Learning? • How Unsupervised Machine Learning works • Types of Unsupervised Learning • Disadvantages of Unsupervised Learning Unsupervised Machine Learning 06
What is Unsupervised Learning? 62 Unsupervised Learning Processing Interpretation • Unknown output • No Training Data Set Input Raw Data Algorithm Output This slide is 100% editable. Adapt it to your needs and capture your audience's attention.
How Unsupervised Machine Learning works 63 This slide is 100% editable. Adapt it to your needs and capture your audience's attention. Provide the machine learning algorithm uncategorized, unlabeled input data to see what patterns it finds Observe and learn from the patterns the machine identifies Step 1 Step 2 Machine Clustering Identifying similarities in groups For Example: Are there patterns in the data to indicate certain patients will respond better to this treatment than others? Anomaly Detection Identifying abnormalities in data For Example: Is a hacker intruding in our network? Types of Problems to Which it’s Suited Similar Group 1 Similar Group 2 Machine
Types of Unsupervised Learning 64 Dimensionality Reduction • Text Mining • Face Recognition • Big Data Visualization • Image Recognition Clustering • Biology • City Planning • Targeted Marketing Unsupervised Learning This slide is 100% editable. Adapt it to your needs and capture your audience's attention.
Disadvantages of Unsupervised Learning 65 You cannot get very specific about the definition of the info sorting and therefore the output. This is often because the info utilized in unsupervised learning is labeled and not known. It's employment of the machine to label and group the data before determining the hidden patterns. The results of the analysis can't be ascertained. there's no prior knowledge within the unsupervised method of machine learning. Additionally, the numbers of classes also are not known. It results in the lack to determine the results generated by the analysis. Less accuracy of the results. This is often also because the input file isn't known and not labeled by people beforehand , which suggests that the machine will got to do that alone.
66 • What is reinforcement learning? • How reinforcement learning works • Types of reinforcement learning • Advantage of reinforcement learning • Disadvantage of reinforcement learning Reinforcement learning 07
What is Reinforcement Learning? 67 This slide is 100% editable. Adapt it to your needs and capture your audience's attention. It’s a mango Wrong! It’s an apple Noted It’s an Apple Reinforced Response Input Response Feedback Learns Input
How Reinforcement Learning Works? 68 Reinforcement Learning Reward State Selection of Algorithm Best Action Agent Environment Output Input Raw Data This slide is 100% editable. Adapt it to your needs and capture your audience's attention.
Types of Reinforcement Learning 69 Gaming Finance Sector Inventory Management Manufacturing Robot Navigation This slide is 100% editable. Adapt it to your needs and capture your audience's attention.
Disadvantage of Reinforcement Learning 70 Less accuracy of the results. this is often also because the input file isn't known and not labeled by people beforehand , which suggests that the machine will got to do that alone. The results of the analysis can't be ascertained. There's no prior knowledge within the unsupervised method of machine learning. Additionally, the numbers of classes also are not known. It results in the lack to determine the results generated by the analysis Reinforcement learning as a framework is wrong in many various ways, but it's precisely this quality that creates it useful. You cannot get very specific about the definition of the info sorting and therefore the output. this is often because the info utilized in unsupervised learning is labeled and not known. it's employment of the machine to label and group the data before determining the hidden patterns. Too much reinforcement learning can cause an overload of states which may diminish the results. Reinforcement learning isn't preferable to use for solving simple problems. Reinforcement learning needs tons of knowledge and tons of computation. it's data-hungry. that's why it works rather well in video games because one can play the sport again and again and again, so getting many data seems feasible. This slide is 100% editable. Adapt it to your needs and capture your audience's attention.
Back Propagation Neural Network in AI 08 71 • Back Propagation Neural Network in AI • What is Artificial Neural Networks? • What is Backpropagation? • Why We Need Backpropagation? • What is a Feed Forward Network? • Types of Backpropagation Networks • Best practice Backpropagation
Back Propagation Neural Network in AI 72 This slide is 100% editable. Adapt it to your needs and capture your audience's attention. w1 b1 b2 h2 2 1 i1 i2 net out
What is Artificial Neural Networks? 73 This slide is 100% editable. Adapt it to your needs and capture your audience's attention. Feed-Forward Network Output Input Layer Network Inputs Hidden Layer Back Propagation Output Layer
What is Backpropagation Neural Networking? 74 This slide is 100% editable. Adapt it to your needs and capture your audience's attention. Difference in Desired Values Backprop Output Layer Input Layer 1 1 Hidden Layer(s) 3 Output Layer 5 x x x w w w w
Why We Need Backpropagation? 75 This slide is 100% editable. Adapt it to your needs and capture your audience's attention. Backpropagation is fast, simple and straightforward to program. It has no parameters to tune aside from the numbers of input. It is a versatile method because it doesn't require prior knowledge about the network. It doesn't need any special mention of the features of the function to be learned. It is a typical method that generally works well. Most prominent advantages of Backpropagation Are:
What is a Feed Forward Network? 76 Input Layer Hidden Layer Output Layer This slide is 100% editable. Adapt it to your needs and capture your audience's attention.
Types of Backpropagation Networks 77 The main difference between both of those methods is: that the mapping is rapid in static back-propagation while it's nonstatic in recurrent backpropagation It is one quite backpropagation network which produces a mapping of a static input for static output. it's useful to unravel static classification issues like optical character recognition. Static Back-propagation Recurrent backpropagation is fed forward until a hard and fast value is achieved. Then, the error is computed and propagated backward. Recurrent Backpropagation • Static Back-propagation • Recurrent Backpropagation
Best Practice Backpropagation 78 A neural network is a group of connected it I/O units where each connection features a weight related to its computer programs. Backpropagation may be a short form for "backward propagation of errors." it's a typical method of coaching artificial neural networks. Backpropagation is fast, simple and straightforward to program. A feedforward neural network is a man-made neural network. BACKPROPAGATION This slide is 100% editable. Adapt it to your needs and capture your audience's attention.
79 • What is an Expert System? • Examples of Expert Systems • Characteristic of Expert System • Components of the expert system • Conventional System vs. Expert system • Human expert vs. expert system • Benefits of expert systems • Limitations of the expert system • Applications of expert systems Expert System in Artificial Intelligence 09
Expert System in Artificial Intelligence 80 The Expert System in AI are computer applications. Also, with the assistance of this development, we will solve complex problems. it's level of human intelligence and expertise This slide is 100% editable. Adapt it to your needs and capture your audience's attention. User (May not be an expert) Knowledge Engineer Human Expert Knowledge Base Inference Engine User Interface
Examples of Expert Systems 81 The Highest Level of Expertise • The expert system offers the very best level of experience. It provides efficiency, accuracy and imaginative problem-solving. Right on Time Reaction • An Expert System interacts during a very reasonable period of your time with the user. the entire time must be but the time taken by an expert to urge the foremost accurate solution for an equivalent problem. Good Reliability • The expert system must be reliable, and it must not make any an error. Flexible • It is significant that it remains flexible because it the is possessed by an Expert system. Capable of Handling Challenging Decision & Problems • An expert system is capable of handling challenging decision problems and delivering solutions. Effective Mechanism • Expert System must have an efficient mechanism to administer the compilation of the prevailing knowledge in it. Expert System User Interface Knowledge Base Inference Engine Non-expert User Knowledge from an expert Query Advice
Characteristic of Expert System 82 This slide is 100% editable. Adapt it to your needs and capture your audience's attention. • Expert systems use symbolic representations for knowledge (rules, networks or frames) and perform their inference through symbolic computations that closely resemble manipulations of tongue Use Symbolic Representations • The system should be designed in such how that it's ready to perform within alittle amount of your time , like or better than the time taken by a person's expert to succeed in at a choice point. An expert system that takes a year to succeed in a choice compared to a person's expert’s time of 1 hour wouldn't be useful Adequate Response Time • The system must be capable of responding at A level of competency adequate to or better than an expert system within the field. the standard of the recommendation given by the system should be during a high level integrity and that the performance ratio should be also very high High level Performance • Expert systems are typically very domain specific. For ex., a diagnostic expert system for troubleshooting computers must actually perform all the required data manipulation as a person's expert would. The developer of such a system must limit his or her scope of the system to only what's needed to unravel the target problem. Special tools or programming languages are often needed to accomplish the precise objectives of the system Domain Specificity • The expert system must be as reliable as a person's expert Good Reliability • The system should be understandable i.e. be ready to explain the steps of reasoning while executing. The expert system should have an evidence capability almost like the reasoning ability of human experts Understandable
Components of the Expert System 83 Explanation Inference Engine Knowledge Base Acquisition Facility User Interface Experts and Knowledge Engineers Users This slide is 100% editable. Adapt it to your needs and capture your audience's attention.
Conventional System vs. Expert System 84 Knowledge domain break away the mechanism processing The program could have made an error Not necessarily need all the input/data Changes within the rule are often made with ease The system can work only with the rule as a tittle Information and processing combined during a sequential file The program isn't wrong Need all the input file Changes to the program are inconvenient The system works if it's complete 01 02 03 04 05 05 04 03 02 01 vs This slide is 100% editable. Adapt it to your needs and capture your audience's attention.
Human Expert vs. Expert System 85 Human Experts (Artificial ) Expert Systems Add Your Text Here Add Your Text Here Difficult to Transfer Easy to Transfer Expensive, especially top notch Affordable, costly to develop, but cheap to operate Difficult to Document Easy to Document Perishable Permanent This slide is 100% editable. Adapt it to your needs and capture your audience's attention.
Benefits of Expert Systems 86 This slide is 100% editable. Adapt it to your needs and capture your audience's attention. Fast Response Easy to Develop and Modify the System Low Accessibility Cost Humans Emotions are not Affected Error Rate are Very Low
Limitations of the Expert System 87 This slide is 100% editable. Adapt it to your needs and capture your audience's attention. Don’t Have Decision Making Power Like Humans Its Difficult to Maintain Its Developed for a Specific Domain Expert System is not Widely used or Tested Not Able to Explain the Logic Behind the Decision It cant Deal with the Mixed Knowledge Development Cost is High There are Chances of Errors
Applications of Expert Systems 88 Knowledge domain (Finding out the faults in vehicles, computer) Finance/Commerce (Stock market trading, airline scheduling cargo scheduling) Process Control System Repairing Monitoring system Medical domain (Diagnosis system, medical operations) Warehousing Optimization Shipping Design domain (Camera lens design,automobile design) This slide is 100% editable. Adapt it to your needs and capture your audience's attention.
Reinforcement Learning in AI PowerPoint Presentation Slide Templates Icons Slide 89
90 Additional Slides Timeline 03 Target 04 Idea Generation 05 Venn 06 Post it notes 07 Thank you 08 Stacked Column 01 Area Chart 02
Stacked Column 91 4.3 2.5 -3.5 -4.5 2.4 4.4 -1.8 -0.8 -6 -4 -2 0 2 4 6 8 Sales in million Product 02 Product 01 This graph/chart is linked to excel, and changes automatically based on data. Just left click on it and select “Edit Data”. Product 01 This graph/chart is linked to excel, and changes automatically based on data. Just left click on it and select “Edit Data”. Product 02
Area Chart 92 4.3 2.5 -3.5 -4.5 2.4 4.4 -1.8 -0.8 -5 -4 -3 -2 -1 0 1 2 3 4 5 Sales in million Product 02 Product 01 This graph/chart is linked to excel, and changes automatically based on data. Just left click on it and select “Edit Data”. Product 01 This graph/chart is linked to excel, and changes automatically based on data. Just left click on it and select “Edit Data”. Product 02
Timeline 93 This slide is 100% editable. Adapt it to your needs and capture your audience's attention. This slide is 100% editable. Adapt it to your needs and capture your audience's attention. This slide is 100% editable. Adapt it to your needs and capture your audience's attention. This slide is 100% editable. Adapt it to your needs and capture your audience's attention. This slide is 100% editable. Adapt it to your needs and capture your audience's attention. This slide is 100% editable. Adapt it to your needs and capture your audience's attention. 2015 2016 2017 2018 2019 2020
Target 94 This slide is 100% editable. Adapt it to your needs and capture your audience's attention. Text Here This slide is 100% editable. Adapt it to your needs and capture your audience's attention. Text Here This slide is 100% editable. Adapt it to your needs and capture your audience's attention. Text Here 01 02 03
Idea Generation 95 02 04 01 03 This slide is 100% editable. Adapt it to your needs and capture your audience's attention. This slide is 100% editable. Adapt it to your needs and capture your audience's attention. This slide is 100% editable. Adapt it to your needs and capture your audience's attention. This slide is 100% editable. Adapt it to your needs and capture your audience's attention.
Venn 96 This slide is 100% editable. Adapt it to your needs and capture your audience's attention. This slide is 100% editable. Adapt it to your needs and capture your audience's attention. This slide is 100% editable. Adapt it to your needs and capture your audience's attention. This slide is 100% editable. Adapt it to your needs and capture your audience's attention. This slide is 100% editable. Adapt it to your needs and capture your audience's attention. Text Here Text Here Text Here Text Here Text Here
Post It Notes 97 01 This slide is 100% editable. Adapt it to your needs and capture your audience's attention. 03 This slide is 100% editable. Adapt it to your needs and capture your audience's attention. 02 This slide is 100% editable. Adapt it to your needs and capture your audience's attention. 04 This slide is 100% editable. Adapt it to your needs and capture your audience's attention.
Thank You 98 Call Us 0123456789 Visit Us # street number, city, state Follow Us emailaddress123@gmail.com

More Related Content

PDF
Artificial Intelligence High Technology PowerPoint Presentation Slides Comple...
bySlideTeam
 
PDF
AI, Machine Learning and Deep Learning - The Overview
bySpotle.ai
 
PPTX
Difference between Artificial Intelligence, Machine Learning, Deep Learning a...
bySanjay Srivastava
 
PPTX
Artificial Intelligence, Machine Learning and Deep Learning
bySujit Pal
 
PDF
Lecture1 AI1 Introduction to artificial intelligence
byAlbert Orriols-Puig
 
PDF
Introduction to machine learning
byRahul Sahai
 
PPTX
Deep Learning
byMoctardOLOULADE
 
PPTX
The Future of Machine Learning
byRussell Miles
 
Artificial Intelligence High Technology PowerPoint Presentation Slides Comple...
bySlideTeam
 
AI, Machine Learning and Deep Learning - The Overview
bySpotle.ai
 
Difference between Artificial Intelligence, Machine Learning, Deep Learning a...
bySanjay Srivastava
 
Artificial Intelligence, Machine Learning and Deep Learning
bySujit Pal
 
Lecture1 AI1 Introduction to artificial intelligence
byAlbert Orriols-Puig
 
Introduction to machine learning
byRahul Sahai
 
Deep Learning
byMoctardOLOULADE
 
The Future of Machine Learning
byRussell Miles
 

What's hot

PDF
AI Vs ML Vs DL PowerPoint Presentation Slide Templates Complete Deck
bySlideTeam
 
PDF
Introduction To Artificial Intelligence Powerpoint Presentation Slides
bySlideTeam
 
PPTX
Supervised and Unsupervised Learning In Machine Learning | Machine Learning T...
bySimplilearn
 
PDF
General introduction to AI ML DL DS
byRoopesh Kohad
 
PPTX
Machine Learning and Real-World Applications
byMachinePulse
 
PDF
Machine learning
byDr Geetha Mohan
 
PDF
Unified Approach to Interpret Machine Learning Model: SHAP + LIME
byDatabricks
 
PDF
An introduction to Machine Learning
bybutest
 
PDF
Lecture1 introduction to machine learning
byUmmeSalmaM1
 
PPTX
Introduction to Deep Learning
byOswald Campesato
 
PPTX
Deep Learning Explained
byMelanie Swan
 
PPTX
Reinforcement Learning
bySalem-Kabbani
 
PPTX
Introduction to Machine Learning
byKmPooja4
 
PPTX
Deep Reinforcement Learning
byUsman Qayyum
 
PDF
Transfer Learning -- The Next Frontier for Machine Learning
bySebastian Ruder
 
PPTX
Intro to Deep Reinforcement Learning
byKhaled Saleh
 
PPTX
supervised learning
byAmar Tripathi
 
PPTX
An introduction to reinforcement learning
bySubrat Panda, PhD
 
PDF
Machine Learning
byShrey Malik
 
PPTX
Machine learning
bySaurabh Agrawal
 
AI Vs ML Vs DL PowerPoint Presentation Slide Templates Complete Deck
bySlideTeam
 
Introduction To Artificial Intelligence Powerpoint Presentation Slides
bySlideTeam
 
Supervised and Unsupervised Learning In Machine Learning | Machine Learning T...
bySimplilearn
 
General introduction to AI ML DL DS
byRoopesh Kohad
 
Machine Learning and Real-World Applications
byMachinePulse
 
Machine learning
byDr Geetha Mohan
 
Unified Approach to Interpret Machine Learning Model: SHAP + LIME
byDatabricks
 
An introduction to Machine Learning
bybutest
 
Lecture1 introduction to machine learning
byUmmeSalmaM1
 
Introduction to Deep Learning
byOswald Campesato
 
Deep Learning Explained
byMelanie Swan
 
Reinforcement Learning
bySalem-Kabbani
 
Introduction to Machine Learning
byKmPooja4
 
Deep Reinforcement Learning
byUsman Qayyum
 
Transfer Learning -- The Next Frontier for Machine Learning
bySebastian Ruder
 
Intro to Deep Reinforcement Learning
byKhaled Saleh
 
supervised learning
byAmar Tripathi
 
An introduction to reinforcement learning
bySubrat Panda, PhD
 
Machine Learning
byShrey Malik
 
Machine learning
bySaurabh Agrawal
 

Similar to Reinforcement Learning In AI Powerpoint Presentation Slide Templates Complete Deck

PPTX
ppt on machine learning to deep learning (1).pptx
byAnweshaGarima
 
PDF
Artificial Intelligence Machine Learning Deep Learning Ppt Powerpoint Present...
bySlideTeam
 
PDF
Artificial Intelligence And Machine Learning PowerPoint Presentation Slides C...
bySlideTeam
 
PDF
Back Propagation Neural Network In AI PowerPoint Presentation Slide Templates...
bySlideTeam
 
PDF
Artificial Intelligence Machine Learning Deep Learning PPT PowerPoint Present...
bySlideTeam
 
PDF
Artificial Intelligence PowerPoint Presentation Slide Template Complete Deck
bySlideTeam
 
PDF
Introduction To Artificial Intelligence PowerPoint Presentation Slides
bySlideTeam
 
PDF
What is artificial intelligence (IA) ?
byOussama Belakhdar
 
PDF
introductiontoartificialintelligencepowerpointpresentationslides-210722041732...
bySudhanshu Gupta
 
PPTX
demo AI ML.pptx
byPriyadharshiniG41
 
PPTX
artificialintelligencemachinelearningdeeplearningpptpowerpointpresentationsli...
bySuthahar
 
PDF
An overview of Artificial intelligence
byVaishali Advani
 
PPTX
artificialintelligenceandmachinelearningpowerpointpresentationslidescompleted...
byrevathi148366
 
PPTX
artificialintelligencedata driven analytics23.pptx
byrevathi148366
 
PPTX
chapter-1-1.pptxmsdsdvsdvnsdvndsvdvds i.
byAkhileshPansare
 
PPTX
Introduction-to-Artificial Intelligence.pptx.pptx
byanirudhamishra440
 
PPTX
Ai and ml brief introduction to the most important
byrio213197
 
PPTX
Artificial Intelligence (AI)Somali heer Jaamacadeed ah.pptx
byGalkayouniversityGU
 
DOCX
one hour presentation content for introduction to....docx
bykannakalamonline
 
PPTX
Machine Learning & AI
byDtech Systems Co.
 
ppt on machine learning to deep learning (1).pptx
byAnweshaGarima
 
Artificial Intelligence Machine Learning Deep Learning Ppt Powerpoint Present...
bySlideTeam
 
Artificial Intelligence And Machine Learning PowerPoint Presentation Slides C...
bySlideTeam
 
Back Propagation Neural Network In AI PowerPoint Presentation Slide Templates...
bySlideTeam
 
Artificial Intelligence Machine Learning Deep Learning PPT PowerPoint Present...
bySlideTeam
 
Artificial Intelligence PowerPoint Presentation Slide Template Complete Deck
bySlideTeam
 
Introduction To Artificial Intelligence PowerPoint Presentation Slides
bySlideTeam
 
What is artificial intelligence (IA) ?
byOussama Belakhdar
 
introductiontoartificialintelligencepowerpointpresentationslides-210722041732...
bySudhanshu Gupta
 
demo AI ML.pptx
byPriyadharshiniG41
 
artificialintelligencemachinelearningdeeplearningpptpowerpointpresentationsli...
bySuthahar
 
An overview of Artificial intelligence
byVaishali Advani
 
artificialintelligenceandmachinelearningpowerpointpresentationslidescompleted...
byrevathi148366
 
artificialintelligencedata driven analytics23.pptx
byrevathi148366
 
chapter-1-1.pptxmsdsdvsdvnsdvndsvdvds i.
byAkhileshPansare
 
Introduction-to-Artificial Intelligence.pptx.pptx
byanirudhamishra440
 
Ai and ml brief introduction to the most important
byrio213197
 
Artificial Intelligence (AI)Somali heer Jaamacadeed ah.pptx
byGalkayouniversityGU
 
one hour presentation content for introduction to....docx
bykannakalamonline
 
Machine Learning & AI
byDtech Systems Co.
 

More from SlideTeam

PDF
ChatGPT IT Powerpoint Presentation Slides
bySlideTeam
 
PDF
Communication Channels And Strategies For Shareholder Engagement Powerpoint P...
bySlideTeam
 
PDF
Designing And Implementing Brand Leadership Strategy Powerpoint Presentation ...
bySlideTeam
 
PDF
Integrating Asset Tracking System To Enhance Operational Effectiveness Comple...
bySlideTeam
 
PDF
Traditional Marketing Channel Analysis Powerpoint Presentation Slides Mkt Cd
bySlideTeam
 
PDF
Word Of Mouth WOM Marketing Strategies To Build Brand Awareness Powerpoint Pr...
bySlideTeam
 
PDF
Product Corporate And Umbrella Branding Powerpoint Presentation Slides Brandi...
bySlideTeam
 
PDF
Strategic Staff Engagement Action Plan Powerpoint Presentation Slides
bySlideTeam
 
PDF
Generating Leads Through Targeted Digital Marketing Campaign Powerpoint Prese...
bySlideTeam
 
PDF
How Amazon Generates Revenues Across Globe Powerpoint Presentation Slides Str...
bySlideTeam
 
PDF
Comprehensive Guide To Sports Marketing Strategy Powerpoint Presentation Slid...
bySlideTeam
 
PDF
Methods To Implement Traditional Marketing Powerpoint Presentation Slides Mkt Cd
bySlideTeam
 
PDF
Customer Support And Services Guide Powerpoint Presentation Slides
bySlideTeam
 
PDF
Developing Flexible Working Practices To Improve Employee Engagement Powerpoi...
bySlideTeam
 
PDF
Responsible Tech Playbook To Leverage Business Ethics Powerpoint Presentation...
bySlideTeam
 
PDF
Boosting Profits With New And Effective Sales Strategic Plan Powerpoint Prese...
bySlideTeam
 
PDF
Unearthing Apples Billion Dollar Branding Secret Powerpoint Presentation Slid...
bySlideTeam
 
PDF
Managing Business Customers Technology Powerpoint Presentation Slides
bySlideTeam
 
PDF
Guide For Effective Event Marketing Powerpoint Presentation Slides Mkt Cd
bySlideTeam
 
PDF
Global Shift Towards Flexible Working Powerpoint Presentation Slides
bySlideTeam
 
ChatGPT IT Powerpoint Presentation Slides
bySlideTeam
 
Communication Channels And Strategies For Shareholder Engagement Powerpoint P...
bySlideTeam
 
Designing And Implementing Brand Leadership Strategy Powerpoint Presentation ...
bySlideTeam
 
Integrating Asset Tracking System To Enhance Operational Effectiveness Comple...
bySlideTeam
 
Traditional Marketing Channel Analysis Powerpoint Presentation Slides Mkt Cd
bySlideTeam
 
Word Of Mouth WOM Marketing Strategies To Build Brand Awareness Powerpoint Pr...
bySlideTeam
 
Product Corporate And Umbrella Branding Powerpoint Presentation Slides Brandi...
bySlideTeam
 
Strategic Staff Engagement Action Plan Powerpoint Presentation Slides
bySlideTeam
 
Generating Leads Through Targeted Digital Marketing Campaign Powerpoint Prese...
bySlideTeam
 
How Amazon Generates Revenues Across Globe Powerpoint Presentation Slides Str...
bySlideTeam
 
Comprehensive Guide To Sports Marketing Strategy Powerpoint Presentation Slid...
bySlideTeam
 
Methods To Implement Traditional Marketing Powerpoint Presentation Slides Mkt Cd
bySlideTeam
 
Customer Support And Services Guide Powerpoint Presentation Slides
bySlideTeam
 
Developing Flexible Working Practices To Improve Employee Engagement Powerpoi...
bySlideTeam
 
Responsible Tech Playbook To Leverage Business Ethics Powerpoint Presentation...
bySlideTeam
 
Boosting Profits With New And Effective Sales Strategic Plan Powerpoint Prese...
bySlideTeam
 
Unearthing Apples Billion Dollar Branding Secret Powerpoint Presentation Slid...
bySlideTeam
 
Managing Business Customers Technology Powerpoint Presentation Slides
bySlideTeam
 
Guide For Effective Event Marketing Powerpoint Presentation Slides Mkt Cd
bySlideTeam
 
Global Shift Towards Flexible Working Powerpoint Presentation Slides
bySlideTeam
 

Recently uploaded

PPTX
This presentation offers an in-depth EXP
byDennisbaraza
 
PDF
A Visual Dictionary Of ArchitectureS.pdf
byAShtabaog1
 
PDF
Garabatos a Freecad. MakeSpace Madrid, 22 noviembre
byLuis Rivera
 
PDF
L6_ES25_Theories of consumption I: Bourdieu.pdf
bymekar24
 
PPTX
UNit_04ofcomputernetworkBCA-Semester5.pptx
byRauank1
 
PDF
Adaptive Controller and Synchronizer Design for Hyperchaotic Zhou System with...
byZac Darcy
 
PDF
09 Mammary glands/ Mammary glands/ Mammary glands.pdf
byProf. Dr. Ahmed Ashour
 
PDF
The Power of Storytelling
byDr. Salem Baidas
 
PDF
MGV Installations 6.pdf Various furniture installations in corporate, healthc...
byManny Vesa
 
PDF
top luxury interior designers london.,,,
byomaraboosama11
 
PDF
05 06 07 Female Reproductive System / Female Reproductive System.pdf
byProf. Dr. Ahmed Ashour
 
PDF
08 Development of Female Reproductive System / Development of Female Reproduc...
byProf. Dr. Ahmed Ashour
 
PDF
010 Bony Pelvis / Bony Pelvi / Bony Pelvis / Bony Pelvis.pdf
byProf. Dr. Ahmed Ashour
 
PDF
Design solutions for modern word issue Alessandra Balestrucci
bybalestruccialessandr
 
PDF
Architecture and Urbanism in Egypt Through the Years
byYasser Mahgoub
 
PPTX
Reviving a Spanish Colonial by the Sea with Antique Carved Doors
byMogul Interior
 
PPT
IRRATkghv sdkvnjhbsdifghuskewafkward egv erwsIONAL 2.ppt
bymangalindanjerremyjh
 
PPTX
COMPENSnfcnbfn ngfn ATORY MECHANISMS IN SHOCK.pptx
byvedprakashsahu251
 
PPTX
architectureandplanningofjaipur-131111094155-phpapp02 (1).pptx
byrakshitgola04
 
PPTX
Shalvika Living Innovations | Premium Handcrafted Wooden Mandirs, Luxury Beds...
bySHALVIKA LIVING INNOVATIONS
 
This presentation offers an in-depth EXP
byDennisbaraza
 
A Visual Dictionary Of ArchitectureS.pdf
byAShtabaog1
 
Garabatos a Freecad. MakeSpace Madrid, 22 noviembre
byLuis Rivera
 
L6_ES25_Theories of consumption I: Bourdieu.pdf
bymekar24
 
UNit_04ofcomputernetworkBCA-Semester5.pptx
byRauank1
 
Adaptive Controller and Synchronizer Design for Hyperchaotic Zhou System with...
byZac Darcy
 
09 Mammary glands/ Mammary glands/ Mammary glands.pdf
byProf. Dr. Ahmed Ashour
 
The Power of Storytelling
byDr. Salem Baidas
 
MGV Installations 6.pdf Various furniture installations in corporate, healthc...
byManny Vesa
 
top luxury interior designers london.,,,
byomaraboosama11
 
05 06 07 Female Reproductive System / Female Reproductive System.pdf
byProf. Dr. Ahmed Ashour
 
08 Development of Female Reproductive System / Development of Female Reproduc...
byProf. Dr. Ahmed Ashour
 
010 Bony Pelvis / Bony Pelvi / Bony Pelvis / Bony Pelvis.pdf
byProf. Dr. Ahmed Ashour
 
Design solutions for modern word issue Alessandra Balestrucci
bybalestruccialessandr
 
Architecture and Urbanism in Egypt Through the Years
byYasser Mahgoub
 
Reviving a Spanish Colonial by the Sea with Antique Carved Doors
byMogul Interior
 
IRRATkghv sdkvnjhbsdifghuskewafkward egv erwsIONAL 2.ppt
bymangalindanjerremyjh
 
COMPENSnfcnbfn ngfn ATORY MECHANISMS IN SHOCK.pptx
byvedprakashsahu251
 
architectureandplanningofjaipur-131111094155-phpapp02 (1).pptx
byrakshitgola04
 
Shalvika Living Innovations | Premium Handcrafted Wooden Mandirs, Luxury Beds...
bySHALVIKA LIVING INNOVATIONS
 

Reinforcement Learning In AI Powerpoint Presentation Slide Templates Complete Deck

  • 1.
    Reinforcement Learning in AIPowerPoint Presentation Slide Templates Y o u r C o m p a n y N a m e
  • 2.
    2 Table of Content Machine Learning •What is Machine Learning? • 7 Steps of Machine learning • Machine Learning vs. Traditional Programming • How does machine learning work? • Machine learning Algorithms • Machine learning use cases • How to choose Machine Learning Algorithm • Why to use decision tree algorithm learning • Challenges and Limitations of Machine learning • Application of Machine learning • Why is machine learning important? Deep Learning • What is Deep Learning? • Deep learning Process • Classification of Neural Networks • Types of Deep Learning Networks • Feed-forward neural networks • Recurrent neural networks (RNNs) • Convolutional neural networks (CNN) • Reinforcement Learning • Examples of deep learning applications • Why is Deep Learning Important? • Limitations of deep learning Difference between AI vs ML vs DL • What is AI? • What is ML? • What is Deep Learning? • Machine Learning Process • Deep Learning Process • Difference between Machine Learning and Deep Learning • Which is better to start AI,ML or Deep learning Introduction • What is AI? • Introduction to AI Levels? • Types of Artificial Intelligence • AI VS machine learning vs deep learning • Where is AI used? • AI use cases • Why is AI booming now? • AI trend in 2020
  • 3.
    3 Table of Content Unsupervised MachineLearning • What is Unsupervised Learning? • How Unsupervised Machine Learning works • Types of Unsupervised Learning • Disadvantages of Unsupervised Learning Reinforcement Learning • What is reinforcement learning? • How reinforcement learning works • Types of reinforcement learning • Advantage of reinforcement learning • Disadvantage of reinforcement learning Expert System in Artificial Intelligence • What is an Expert System? • Examples of Expert Systems • Characteristic of Expert System • Components of the expert system • Conventional System vs. Expert system • Human expert vs. expert system • Benefits of expert systems • Limitations of the expert system • Applications of expert systems Back Propagation Neural Network in AI • Back Propagation Neural Network in AI • What is Artificial Neural Networks? • What is Backpropagation? • Why We Need Backpropagation? • What is a Feed Forward Network? • Types of Backpropagation Networks • Best practice Backpropagation Supervised Machine Learning • Types of Machine Learning • What is Supervised Machine Learning? • How Supervised Learning Works • Types of Supervised Machine Learning Algorithms • Supervised vs. Unsupervised Machine learning techniques • Advantages of Supervised Learning • Disadvantages of Supervised Learning
  • 4.
    4 Introduction 01 • What isAI? • Introduction to AI Levels? • Types of Artificial Intelligence • AI VS machine learning vs deep learning • Where is AI used? • AI use cases • Why is AI booming now? • AI trend in 2020
  • 5.
    5 Transforming the Natureof Work, Learning, and Learning to Work Artificial intelligence (AI) is a popular branch of computer science that concerns with building “intelligent” smart machines capable of performing intelligent tasks. With rapid advancements in deep learning and machine learning, the tech industry is transforming radically. Artificial Intelligence Deep Learning Machine Learning This slide is 100% editable. Adapt it to your needs and capture your audience's attention. Artificial Intelligence
  • 6.
    Introduction to AILevels? 6 Artificial Narrow Intelligence Artificial General Intelligence Artificial Super Intelligence Types of Artificial Intelligence This slide is 100% editable. Adapt it to your needs and capture your audience's attention.
  • 7.
    Types of ArtificialIntelligence 7 This slide is 100% editable. Adapt it to your needs and capture your audience's attention. Machine Learning Artificial Intelligence Deep Learning
  • 8.
    Artificial Intelligence 8 2020 2019 2018 2020 20192018 AI 2016 2017 2018 2019 2020 AI 65% 35% Artificial intelligence (AI) is a popular branch of computer science that concerns with building “intelligent” smart machines capable of performing intelligent tasks. With rapid advancements in deep learning and machine learning, the tech industry is transforming radically. This slide is 100% editable. Adapt it to your needs and capture your audience's attention This slide is 100% editable. Adapt it to your needs and capture your audience's attention This slide is 100% editable. Adapt it to your needs and capture your audience's attention This slide is 100% editable. Adapt it to your needs and capture your audience's attention This slide is 100% editable. Adapt it to your needs and capture your audience's attention This slide is 100% editable. Adapt it to your needs and capture your audience's attention This slide is 100% editable. Adapt it to your needs and capture your audience's attention This slide is 100% editable. Adapt it to your needs and capture your audience's attention This slide is 100% editable. Adapt it to your needs and capture your audience's attention
  • 9.
    Machine Learning 9 Machine learningis a type of AI that enables machines to learn from data and deliver predictive models. The machine learning is not dependent on any explicit programming but the data fed into it. It is a complicated process. Based on the data you feed into machine learning algorithm and the training given to it, an output is delivered. A predictive algorithm will create a predictive model. This slide is 100% editable. Adapt it to your needs and capture your audience's attention.
  • 10.
    Deep Learning 10 This slideis 100% editable. Adapt it to your needs and capture your audience's attention. Deep Learning is a subfield of machine learning that is concerned with algorithms inspired by the brain's structure A computer model can be taught using Deep Learning to run classification actions using pictures, texts or sounds as input functions known as artificial neural networks &
  • 11.
    AI VS MachineLearning VS Deep Learning 11 • Machine Learning originated around 1960s • Machine learning is the practice of getting machines to make decisions without being programmed • Machine learning is a subset of AI & Data Science • Aim is to make machines learn through data so that they can solve problems Machine Learning • Deep Learning originated around 1970s • Deep Learning is the process of using artificial neural networks to solve complex problems • Deep Learning is a subset of Machine Learning, AI & Data Science • Aim is to build neural networks that au6tonetically discover patterns for feature detection Deep Learning • Artificial Intelligence originated around 1950s • AI represents simulate intelligence in machines • AI is a subset of data science • Aim is to build machines which are capable of thinking like humans Artificial Intelligence This slide is 100% editable. Adapt it to your needs and capture your audience's attention.
  • 12.
    Where is AIused? 12 Customer Experience Supply Chain Human Resources Knowledge Creation Research & Development Fraud Detection Real-time Operations Management Customer Services Risk Management & Analytics Customer Insight Pricing & Promotion Predictive Analytics This slide is 100% editable. Adapt it to your needs and capture your audience's attention.
  • 13.
    AI Usecase inHealthCare 13 AI and Robotics Research Keeping Well Early Detection Diagnosis Decision Making Treatment End of Life Care Training This slide is 100% editable. Adapt it to your needs and capture your audience's attention.
  • 14.
    AI Use Casesin Human Resource 14 LEARNING • Curated Training • Skill Development RECRUITING • Dynamic Career Sites • Smart Sourcing ENGAGEMENT • HR Chatbot • Engagement Surveys ONBOARDING • Automated Messages • Curated Videos Employee Life Cycle This slide is 100% editable. Adapt it to your needs and capture your audience's attention.
  • 15.
    AI in Bankingfor Fraud Detection 15 Configuration Workstation Expert Rules Execute Rules Definition Neural Network Engine Scoring Engine Authorization System Case Creation Module Case Management Database Expert Authorization Response Module Expert Rules Base Cardholder Profiles Postings Payment System Nonmonetary System Analyst Workstation Auth Request Case Creation Rules Execute Payment and Non-Monetary Transactions Auth Recommendation Auth Request & Score Transaction & Score Case Information 08 01 02 05 06 07 04 03 This slide is 100% editable. Adapt it to your needs and capture your audience's attention.
  • 16.
    AI in SupplyChain 16 Logistics Service Procurement Manufacturing Customers Pervasive Visibility Proactive Replenishment Predictive Maintenance IIOT – Securely Provisionally People, System and Things Digital Ecosystem Data Lake Secure Access Via Identity Management for Transient Users Secure Device Maintenance Unified Messaging Actionable Insights Ecosystem Integration Structured & Unstructured Information Regulatory Data B2B Transaction Data Inventory Data Multimedia Data Sensor Data Logistics Data Trading Partner Data Social Media Data This slide is 100% editable. Adapt it to your needs and capture your audience's attention.
  • 17.
    Ai Chatbots inHealthcare 17 Search Engine Users learn to search for information Social Platforms Like Facebook connect users online Smartphones Bring the internet online App Eco-system Lets users download and use apps easily Messenger Apps Lets users chat anywhere, anytime Artificial Intelligence Self Learning machines becomes smarter the more they are used Healthbots Bring all of the above together for healthcare use cases This slide is 100% editable. Adapt it to your needs and capture your audience's attention.
  • 18.
    Why is AIbooming now? 18 100% 92% 84% 45% 54% United States China India Germany Israel 22% 24% 27% 36% 37% 51% 60% 60% 66% 71% 0 20 40 60 80 100 Fleet Mobile Expediting Transactions Production Floor Systems Logistics & Supply Chain Monitoring Through External Devices/Systems Operational Environment HR/Workforce Management Security/Fraud Customer Relation/Interaction (i.e., chatbots) External Communication 8,097 7,540 7,336 4,680 4,201 3,714 3,655 3,564 3,169 0 2,000 4,000 6,000 8,000 Static Image Recognition, Classification and Tagging Algorithm Trading Strategy Performance Management Efficient, Scalable Processing of Patient Data Predictive Maintenance Object Identification, detection, classification, tracking Text Query of Images Automated Geophysical Feature Detection Content Distribution on Social Media Object detection & classification, avoidance, navigation Global AI Revenue Forecast by 2025, Ranked by Use Case in millions US Dollar Penetration of Artificial Intelligence Skills, by Country Organizations deploying AI, by Functional Areas
  • 19.
    10 AI Trendin 2020 19 AI Trends” “2020 Robotic Process Automation AI will make Healthcare more Accurate Data Modeling will move to the Edge AI will Come for B2B Ai-powered Chatbots AI In Retail Aerospace and Flight Operations Controlled by AI AI Mediated Media and Entertainment Advanced Cybersecurity Automated Business Process This slide is 100% editable. Adapt it to your needs and capture your audience's attention.
  • 20.
    20 • What isMachine Learning? • 7 Steps of Machine learning • Machine Learning vs. Traditional Programming • How does machine learning work? • Machine learning Algorithms • Machine learning use cases • How to choose Machine Learning Algorithm • Why to use decision tree algorithm learning • Challenges and Limitations of Machine learning • Application of Machine learning • Why is machine learning important? Machine Learning 02
  • 21.
    Machine Learning 21 Machine Learningis the result of General AI that involves developing machines that can deliver results better than humans Input Data: Feed Learner Various Data Output Data: Present Rules “Learning” Machine Learning System Traditional Programming Data (Input) Program Output Data (Input) Output Machine Learning Program This slide is 100% editable. Adapt it to your needs and capture your audience's attention.
  • 22.
    7 Steps ofMachine Learning 22 This slide is 100% editable. Adapt it to your needs and capture your audience's attention. Gathering Data Preparing that Data Choosing a Model Training Evaluation Hyperparameter Tuning Prediction
  • 23.
    Machine Learning vs.Traditional Programming 23 Machine Learning Learning Model Sample Data Expected Result Computer Prediction Result New Data Model Computer Prediction Result Computer Data Handcrafted Model Traditional Modelling This slide is 100% editable. Adapt it to your needs and capture your audience's attention.
  • 24.
    How does MachineLearning Work? 24 This slide is 100% editable. Adapt it to your needs and capture your audience's attention. Identify, the problem to be solved and create a clear objective. Define Objectives Preparing data is a crucial step and involves building workflows to clean, match and blend the data. Prepare Data Data is fed as input and the algorithm configured with the required parameters. A percent of the data can be utilized to train the model. Train Model Publish the prepared experiment as a web service, so applications can use the model. Integrate Model Collect data from hospitals, health insurance companies, social service agencies, police and fire dept. Collect Data Depend on the problem to be solved and the type of data an appropriate algorithm will be chosen. Select Algorithm The remaining data is utilized to test the model, for accuracy. Depending on the results, improvements, can be performed in the “Train model’ and/or “Select Algorithm” phases, iteratively. Test Model
  • 25.
    Machine Learning Algorithms 25 Thisslide is 100% editable. Adapt it to your needs and capture your audience's attention. • Linear • Polynomial • KNN • Trees • Logistic Regression • Naïve-Bayes • SVM • SVD • PCA • K-means • Apriori • FP-Growth Reinforcement Machine Learning Regression Clustering Decision Tree Classification Association Anlaysis Supervised Unsupervised Random Forest Hidden Markov Model Continuous Categorical
  • 26.
    Machine Learning UseCases 26 This slide is 100% editable. Adapt it to your needs and capture your audience's attention. Energy Feedstock & Utilities • Power Usage Analytics • Seismic Data Processing • Your Text Here • Smart Grid Management • Energy Demand & Supply Optimization Financial Services • Risk Analytics & Regulation • Customer Segmentation • Your Text Here • Credit Worthiness Evaluation Travel & Hospitality • Aircraft Scheduling • Dynamic Pricing • Your Text Here • Traffic Patterns & Congestion Management Manufacturing • Predictive Maintenance or Condition Monitoring • Your Text Here • Demand Forecasting • Process Optimization • Telematics Retail • Predictive Inventory Planning • Recommendation Engines • Your Text Here • Customer ROI & Lifetime Value Healthcare & Life Sciences • Alerts & Diagnostics from Real-time Patient Data • Your Text Here • Predictive Health Management • Healthcare Provider Sentiment Analysis
  • 27.
    How to ChooseMachine Learning Algorithm 27 This slide is 100% editable. Adapt it to your needs and capture your audience's attention. What do you want to do with your Data? Additional Requirements Accuracy Linearity Number of Parameters Training Time Number of Features How to Select Machine Learning Algorithms Algorithm Cheat Sheet
  • 28.
    Why use DecisionTree Machine Learning Algorithm? 28 This slide is 100% editable. Adapt it to your needs and capture your audience's attention. Decision Trees To Classify Responsible Variable has only 2 Categories Response Variable has Multiple Categories Use Standard Classification here Use c4.5 Implementation Non-linear Relationship between Predictors & Response Linear Relationship between Predictors & Response Use c4.5 Implementation Use Standard Regression Tree To Predict Responsible variable is Continuous
  • 29.
    Challenges and Limitationsof Machine learning 29 This slide is 100% editable. Adapt it to your needs and capture your audience's attention. Advantages Disadvantages Easily Identifies Trends and Patterns No Human Intervention needed Handling multi-dimensional & multi-variety Data Continuous Improvement Wide Applications Data Acquisition High error- Susceptibility Time and Resources Interpretation Results
  • 30.
    Application of MachineLearning 30 This slide is 100% editable. Adapt it to your needs and capture your audience's attention. Automatic Language Translation Medical Diagnosis Stock Market Trading Online Fraud Detection Virtual Personal Assistant Email Spam and Malware Filtering Self Driving Cars Product Recommendations Traffic Prediction Speech Recognition Image Recognition
  • 31.
    Why is MachineLearning Important? 31 This slide is 100% editable. Adapt it to your needs and capture your audience's attention. Training Data • Normalization • Dimension Reduction • Image Processing, etc. Pre-Processing • Supervised • Unsupervised • Minimization, etc. Learning • Precision/recall • Over fitting • Test/cross Validation data, etc. Error Analysis Phase 2: Prediction Phase 1 : Learning Model New Data Predicted Data Prediction
  • 32.
    32 • What isDeep Learning? • Deep learning Process • Classification of Neural Networks • Types of Deep Learning Networks • Feed-forward neural networks • Recurrent neural networks (RNNs) • Convolutional neural networks (CNN) • Reinforcement Learning • Examples of deep learning applications • Why is Deep Learning Important? • Limitations of deep learning Deep Learning 03
  • 33.
    What is DeepLearning? 33 Input Feature Extraction + Classification Output Car Not Car What is Deep Learning? Deep Learning is a subfield of machine learning that is concerned with algorithms inspired by the brain's structure and functions known as artificial neural networks. A computer model can be taught using Deep Learning to run classification actions using pictures, texts or sounds as input. This slide is 100% editable. Adapt it to your needs and capture your audience's attention.
  • 34.
    Deep Learning Process 34 Thisslide is 100% editable. Adapt it to your needs and capture your audience's attention. Understand the Problem Identify Data Select Deep Learning Algorithms Training the Model Test the Model
  • 35.
    Classification of NeuralNetworks 35 This slide is 100% editable. Adapt it to your needs and capture your audience's attention. x1 x2 xn v11 v12 vpn w11 w22 wmp ym y2 y1 1 2 m V1n w1p Input Layer Hidden Layer Output Layer 1 2 p
  • 36.
    Types of DeepLearning Networks 36 Supervised Artificial Neural Networks Used for Regression & Classification Convolutional Neural Networks Used for Computer Vision Recurrent Neutral Networks Used for Time Series Analysis Unsupervised Self-Organizing Maps Used for Feature Detection Deep Boltzmann Machines Used for Recommendation Systems AutoEncoders Used for Recommendation Systems Deep Learning Models • Artificial Neural Networks (ANN) • Convolutional Neural Networks (CNN) • Recurrent Neural Networks (RNN) Supervised • Self Organizing Maps (SOM) • Boltzmann Machines (BM) • AutoEncoders (AE) Unsupervised This slide is 100% editable. Adapt it to your needs and capture your audience's attention.
  • 37.
    Feed-forward Neural Networks 37 Thisslide is 100% editable. Adapt it to your needs and capture your audience's attention. Input Layer Hidden Layer Output Layer Variable- #1 Variable- #2 Variable- #3 Variable- # 4 Output
  • 38.
    Recurrent Neural Networks(RNNs) 38 This slide is 100% editable. Adapt it to your needs and capture your audience's attention. Input Layer Recurrent Network Output Layer Hidden Layers x1 x2 y
  • 39.
    Convolutional Neural Networks(CNN) 39 Take Car = A1 Truck = B1 VAN = C1 Bicycle = D1 Rest all be Same This slide is 100% editable. Adapt it to your needs and capture your audience's attention.
  • 40.
    Reinforcement Learning 40 Reinforcement Learning usesrewards and punishment to train computing models to perform a sequence of selections. Here computing faces a game-like scenario where it employs trial and error to answer. Based on the action it performs, computing gets either rewards or penalties. Its goal is to maximize the rewards. Action State, Reward Agent Environment Exploration Policy Filters Algorithm Neural Networks Memory This slide is 100% editable. Adapt it to your needs and capture your audience's attention.
  • 41.
    Examples of DeepLearning Applications 41 Image Recognition Portfolio Management & Prediction of Stock Price Movements Speech Recognition Natural Language Processing Drug Discovery & Better Diagnostics of Diseases in Healthcare Robots and Self - Driving Cars This slide is 100% editable. Adapt it to your needs and capture your audience's attention.
  • 42.
    Why is DeepLearning Important? 42 Deep Learning Other Learning Algorithms Performance Data This slide is 100% editable. Adapt it to your needs and capture your audience's attention.
  • 43.
    Limitations of DeepLearning 43 Interpretability Statistical Reasoning Amount of Data Limitations of Deep Learning This slide is 100% editable. Adapt it to your needs and capture your audience's attention.
  • 44.
    44 • What isAI? • What is ML? • What is Deep Learning? • Machine Learning Process • Deep Learning Process • Difference between Machine Learning and Deep Learning • Which is better to start AI,ML or Deep learning Difference between AI vs ML vs DL 04
  • 45.
    Difference between AIvs ML vs DL 45 Engineering of making intelligent machines and programs Artificial Intelligence Ability to learn without being explicitly programmed Machine Learning Learning based on deep neural network Deep Learning This slide is 100% editable. Adapt it to your needs and capture your audience's attention.
  • 46.
    What is AI? 46 Artificialintelligence (AI) is a popular branch of computer science that concerns with building “intelligent” smart machines capable of performing intelligent tasks. With rapid advancements in deep learning and machine learning, the tech industry is transforming radically. This slide is 100% editable. Adapt it to your needs and capture your audience's attention.
  • 47.
    What is ML? 47 Thisslide is 100% editable. Adapt it to your needs and capture your audience's attention. Machine Learning is a type of AI that enables machines to learn from data and deliver predictive models. The machine learning is not dependent on any explicit programming but the data fed into it. It is a complicated process. Based on the data you feed into machine learning algorithm and the training given to it, an output is delivered. A predictive algorithm will create a predictive model. Learns Predicts Improves Machine Learning Ordinary System With AI Introduction to Machine learning
  • 48.
    What is DeepLearning? 48 This slide is 100% editable. Adapt it to your needs and capture your audience's attention. Deep Learning Artificial intelligence (AI) is a popular branch of computer science that concerns with building “intelligent” smart machines capable of performing intelligent tasks. With rapid advancements in deep learning and machine learning, the tech industry is transforming radically.
  • 49.
    Machine Learning Process 49 Data Gathering Building Model& Finalising Data Transformation into Predictions Data Cleaning Selecting Right Algorithms Modelling Candidate & Final Visualisation Predictions & Strategy Data Raw & Training Data This slide is 100% editable. Adapt it to your needs and capture your audience's attention.
  • 50.
    Deep Learning Process 50 Thisslide is 100% editable. Adapt it to your needs and capture your audience's attention. Understand the Problem Identify Data Select Deep Learning Algorithm Training the Model Test the Model
  • 51.
    Difference between MachineLearning and Deep Learning 51 Feature Extraction Classification Output Car Not Car Input Machine Learning Deep Learning Feature Extraction + Classification Car Not Car Output Input This slide is 100% editable. Adapt it to your needs and capture your audience's attention.
  • 52.
    Which is betterto start AI,ML or DL? 52 Subset of AI Techniques which use Statistical Methods to Enable Machines to Improve with Experiences. Machine Learning Any Technique which enables computers to mimic human behavior. Artificial Intelligence Subset of ML which make the Computation of Multi- layer Neural Networks Feasible. Deep Learning This slide is 100% editable. Adapt it to your needs and capture your audience's attention.
  • 53.
    53 Supervised Machine Learning 05 •Types of Machine Learning • What is Supervised Machine Learning? • How Supervised Learning Works • Types of Supervised Machine Learning Algorithms • Supervised vs. Unsupervised Machine learning techniques • Advantages of Supervised Learning: • Disadvantages of Supervised Learning
  • 54.
    Types of MachineLearning 54 This slide is 100% editable. Adapt it to your needs and capture your audience's attention. Supervised Learning Unsupervised Learning Reinforcement Learning Makes Machine Learn Explicitly Data with Clearly defined Output is given Direct feedback is given Predicts outcome/future Resolves Classification and Regression Problems Training Inputs Outputs Machine Understands the data (Identifies Patterns/ Structures) Evaluation is Qualitative or Indirect Does not Predict/Find anything Specific Inputs Outputs An approach to AI Reward Based Learning Learning form +ve & +ve Reinforcement Machine Learns how to act in a Certain Environment To Maximize Rewards Rewards Inputs Outputs
  • 55.
    What is SupervisedMachine Learning? 55 Supervised Learning This slide is 100% editable. Adapt it to your needs and capture your audience's attention. Input Raw Data Processing Output Algorithm Training Data set Desired Output Supervisor
  • 56.
    How Supervised MachineLearning works 56 Provide the Machine Learning Algorithm Categorized or “labeled” Input and Output Data from to Learn Feed the Machine New, Unlabeled Information to See if it Tags New Data Appropriately. If not, Continue Refining the Algorithm Step 1 Step 2 Types of Problems to Which it’s Suited Machine Label “Group 1” Machine Group 1 Group 2 Classification Sorting Items into Categories Regression Identifying Real Values (Dollars, Weight, etc.)
  • 57.
    Types of SupervisedMachine Learning Algorithms 57 This slide is 100% editable. Adapt it to your needs and capture your audience's attention. Classification • Fraud Detection • Email Spam Detection • Diagnostics • Image Classification Regression • Risk Assessment • Score Prediction Supervised Learning
  • 58.
    Supervised vs. UnsupervisedMachine Learning Techniques 58 This slide is 100% editable. Adapt it to your needs and capture your audience's attention. Supervised Learning • Classification • Regression Input & Output Data Predictions & Predictive Models Unsupervised Learning • Clustering • Association Input Data Patterns / Structure Discovery vs
  • 59.
    Advantages of SupervisedLearning 59 Advantages It allows you to be very specific about the definition of the labels. In other words, you'll train the algorithm to differentiate different classes where you'll set a perfect decision boundary. You are ready to determine the amount of classes you would like to possess. The input file is extremely documented and is labeled. The results produced by the supervised method are more accurate and reliable as compared to the results produced by the unsupervised techniques of machine learning. this is often mainly because the input file within the supervised algorithm is documented and labeled. this is often a key difference between supervised and unsupervised learning. The answers within the analysis and therefore the output of your algorithm are likely to be known thanks to that each one the classes used are known. This slide is 100% editable. Adapt it to your needs and capture your audience's attention.
  • 60.
    Disadvantages of SupervisedLearning 60 Disadvantages • Supervised learning are often a posh method as compared with the unsupervised method. The key reason is that you simply need to understand alright and label the inputs in supervised learning. • It doesn’t happen in real time while the unsupervised learning is about the important time. this is often also a serious difference between supervised and unsupervised learning. Supervised machine learning uses of-line analysis. • It is needed tons of computation time for training. • If you've got a dynamic big and growing data, you're unsure of the labels to predefine the principles. this will be a true challenge. This slide is 100% editable. Adapt it to your needs and capture your audience's attention.
  • 61.
    61 • What isUnsupervised Learning? • How Unsupervised Machine Learning works • Types of Unsupervised Learning • Disadvantages of Unsupervised Learning Unsupervised Machine Learning 06
  • 62.
    What is UnsupervisedLearning? 62 Unsupervised Learning Processing Interpretation • Unknown output • No Training Data Set Input Raw Data Algorithm Output This slide is 100% editable. Adapt it to your needs and capture your audience's attention.
  • 63.
    How Unsupervised MachineLearning works 63 This slide is 100% editable. Adapt it to your needs and capture your audience's attention. Provide the machine learning algorithm uncategorized, unlabeled input data to see what patterns it finds Observe and learn from the patterns the machine identifies Step 1 Step 2 Machine Clustering Identifying similarities in groups For Example: Are there patterns in the data to indicate certain patients will respond better to this treatment than others? Anomaly Detection Identifying abnormalities in data For Example: Is a hacker intruding in our network? Types of Problems to Which it’s Suited Similar Group 1 Similar Group 2 Machine
  • 64.
    Types of UnsupervisedLearning 64 Dimensionality Reduction • Text Mining • Face Recognition • Big Data Visualization • Image Recognition Clustering • Biology • City Planning • Targeted Marketing Unsupervised Learning This slide is 100% editable. Adapt it to your needs and capture your audience's attention.
  • 65.
    Disadvantages of UnsupervisedLearning 65 You cannot get very specific about the definition of the info sorting and therefore the output. This is often because the info utilized in unsupervised learning is labeled and not known. It's employment of the machine to label and group the data before determining the hidden patterns. The results of the analysis can't be ascertained. there's no prior knowledge within the unsupervised method of machine learning. Additionally, the numbers of classes also are not known. It results in the lack to determine the results generated by the analysis. Less accuracy of the results. This is often also because the input file isn't known and not labeled by people beforehand , which suggests that the machine will got to do that alone.
  • 66.
    66 • What isreinforcement learning? • How reinforcement learning works • Types of reinforcement learning • Advantage of reinforcement learning • Disadvantage of reinforcement learning Reinforcement learning 07
  • 67.
    What is ReinforcementLearning? 67 This slide is 100% editable. Adapt it to your needs and capture your audience's attention. It’s a mango Wrong! It’s an apple Noted It’s an Apple Reinforced Response Input Response Feedback Learns Input
  • 68.
    How Reinforcement LearningWorks? 68 Reinforcement Learning Reward State Selection of Algorithm Best Action Agent Environment Output Input Raw Data This slide is 100% editable. Adapt it to your needs and capture your audience's attention.
  • 69.
    Types of ReinforcementLearning 69 Gaming Finance Sector Inventory Management Manufacturing Robot Navigation This slide is 100% editable. Adapt it to your needs and capture your audience's attention.
  • 70.
    Disadvantage of ReinforcementLearning 70 Less accuracy of the results. this is often also because the input file isn't known and not labeled by people beforehand , which suggests that the machine will got to do that alone. The results of the analysis can't be ascertained. There's no prior knowledge within the unsupervised method of machine learning. Additionally, the numbers of classes also are not known. It results in the lack to determine the results generated by the analysis Reinforcement learning as a framework is wrong in many various ways, but it's precisely this quality that creates it useful. You cannot get very specific about the definition of the info sorting and therefore the output. this is often because the info utilized in unsupervised learning is labeled and not known. it's employment of the machine to label and group the data before determining the hidden patterns. Too much reinforcement learning can cause an overload of states which may diminish the results. Reinforcement learning isn't preferable to use for solving simple problems. Reinforcement learning needs tons of knowledge and tons of computation. it's data-hungry. that's why it works rather well in video games because one can play the sport again and again and again, so getting many data seems feasible. This slide is 100% editable. Adapt it to your needs and capture your audience's attention.
  • 71.
    Back Propagation NeuralNetwork in AI 08 71 • Back Propagation Neural Network in AI • What is Artificial Neural Networks? • What is Backpropagation? • Why We Need Backpropagation? • What is a Feed Forward Network? • Types of Backpropagation Networks • Best practice Backpropagation
  • 72.
    Back Propagation NeuralNetwork in AI 72 This slide is 100% editable. Adapt it to your needs and capture your audience's attention. w1 b1 b2 h2 2 1 i1 i2 net out
  • 73.
    What is ArtificialNeural Networks? 73 This slide is 100% editable. Adapt it to your needs and capture your audience's attention. Feed-Forward Network Output Input Layer Network Inputs Hidden Layer Back Propagation Output Layer
  • 74.
    What is BackpropagationNeural Networking? 74 This slide is 100% editable. Adapt it to your needs and capture your audience's attention. Difference in Desired Values Backprop Output Layer Input Layer 1 1 Hidden Layer(s) 3 Output Layer 5 x x x w w w w
  • 75.
    Why We NeedBackpropagation? 75 This slide is 100% editable. Adapt it to your needs and capture your audience's attention. Backpropagation is fast, simple and straightforward to program. It has no parameters to tune aside from the numbers of input. It is a versatile method because it doesn't require prior knowledge about the network. It doesn't need any special mention of the features of the function to be learned. It is a typical method that generally works well. Most prominent advantages of Backpropagation Are:
  • 76.
    What is aFeed Forward Network? 76 Input Layer Hidden Layer Output Layer This slide is 100% editable. Adapt it to your needs and capture your audience's attention.
  • 77.
    Types of BackpropagationNetworks 77 The main difference between both of those methods is: that the mapping is rapid in static back-propagation while it's nonstatic in recurrent backpropagation It is one quite backpropagation network which produces a mapping of a static input for static output. it's useful to unravel static classification issues like optical character recognition. Static Back-propagation Recurrent backpropagation is fed forward until a hard and fast value is achieved. Then, the error is computed and propagated backward. Recurrent Backpropagation • Static Back-propagation • Recurrent Backpropagation
  • 78.
    Best Practice Backpropagation 78 Aneural network is a group of connected it I/O units where each connection features a weight related to its computer programs. Backpropagation may be a short form for "backward propagation of errors." it's a typical method of coaching artificial neural networks. Backpropagation is fast, simple and straightforward to program. A feedforward neural network is a man-made neural network. BACKPROPAGATION This slide is 100% editable. Adapt it to your needs and capture your audience's attention.
  • 79.
    79 • What isan Expert System? • Examples of Expert Systems • Characteristic of Expert System • Components of the expert system • Conventional System vs. Expert system • Human expert vs. expert system • Benefits of expert systems • Limitations of the expert system • Applications of expert systems Expert System in Artificial Intelligence 09
  • 80.
    Expert System inArtificial Intelligence 80 The Expert System in AI are computer applications. Also, with the assistance of this development, we will solve complex problems. it's level of human intelligence and expertise This slide is 100% editable. Adapt it to your needs and capture your audience's attention. User (May not be an expert) Knowledge Engineer Human Expert Knowledge Base Inference Engine User Interface
  • 81.
    Examples of ExpertSystems 81 The Highest Level of Expertise • The expert system offers the very best level of experience. It provides efficiency, accuracy and imaginative problem-solving. Right on Time Reaction • An Expert System interacts during a very reasonable period of your time with the user. the entire time must be but the time taken by an expert to urge the foremost accurate solution for an equivalent problem. Good Reliability • The expert system must be reliable, and it must not make any an error. Flexible • It is significant that it remains flexible because it the is possessed by an Expert system. Capable of Handling Challenging Decision & Problems • An expert system is capable of handling challenging decision problems and delivering solutions. Effective Mechanism • Expert System must have an efficient mechanism to administer the compilation of the prevailing knowledge in it. Expert System User Interface Knowledge Base Inference Engine Non-expert User Knowledge from an expert Query Advice
  • 82.
    Characteristic of ExpertSystem 82 This slide is 100% editable. Adapt it to your needs and capture your audience's attention. • Expert systems use symbolic representations for knowledge (rules, networks or frames) and perform their inference through symbolic computations that closely resemble manipulations of tongue Use Symbolic Representations • The system should be designed in such how that it's ready to perform within alittle amount of your time , like or better than the time taken by a person's expert to succeed in at a choice point. An expert system that takes a year to succeed in a choice compared to a person's expert’s time of 1 hour wouldn't be useful Adequate Response Time • The system must be capable of responding at A level of competency adequate to or better than an expert system within the field. the standard of the recommendation given by the system should be during a high level integrity and that the performance ratio should be also very high High level Performance • Expert systems are typically very domain specific. For ex., a diagnostic expert system for troubleshooting computers must actually perform all the required data manipulation as a person's expert would. The developer of such a system must limit his or her scope of the system to only what's needed to unravel the target problem. Special tools or programming languages are often needed to accomplish the precise objectives of the system Domain Specificity • The expert system must be as reliable as a person's expert Good Reliability • The system should be understandable i.e. be ready to explain the steps of reasoning while executing. The expert system should have an evidence capability almost like the reasoning ability of human experts Understandable
  • 83.
    Components of theExpert System 83 Explanation Inference Engine Knowledge Base Acquisition Facility User Interface Experts and Knowledge Engineers Users This slide is 100% editable. Adapt it to your needs and capture your audience's attention.
  • 84.
    Conventional System vs.Expert System 84 Knowledge domain break away the mechanism processing The program could have made an error Not necessarily need all the input/data Changes within the rule are often made with ease The system can work only with the rule as a tittle Information and processing combined during a sequential file The program isn't wrong Need all the input file Changes to the program are inconvenient The system works if it's complete 01 02 03 04 05 05 04 03 02 01 vs This slide is 100% editable. Adapt it to your needs and capture your audience's attention.
  • 85.
    Human Expert vs.Expert System 85 Human Experts (Artificial ) Expert Systems Add Your Text Here Add Your Text Here Difficult to Transfer Easy to Transfer Expensive, especially top notch Affordable, costly to develop, but cheap to operate Difficult to Document Easy to Document Perishable Permanent This slide is 100% editable. Adapt it to your needs and capture your audience's attention.
  • 86.
    Benefits of ExpertSystems 86 This slide is 100% editable. Adapt it to your needs and capture your audience's attention. Fast Response Easy to Develop and Modify the System Low Accessibility Cost Humans Emotions are not Affected Error Rate are Very Low
  • 87.
    Limitations of theExpert System 87 This slide is 100% editable. Adapt it to your needs and capture your audience's attention. Don’t Have Decision Making Power Like Humans Its Difficult to Maintain Its Developed for a Specific Domain Expert System is not Widely used or Tested Not Able to Explain the Logic Behind the Decision It cant Deal with the Mixed Knowledge Development Cost is High There are Chances of Errors
  • 88.
    Applications of ExpertSystems 88 Knowledge domain (Finding out the faults in vehicles, computer) Finance/Commerce (Stock market trading, airline scheduling cargo scheduling) Process Control System Repairing Monitoring system Medical domain (Diagnosis system, medical operations) Warehousing Optimization Shipping Design domain (Camera lens design,automobile design) This slide is 100% editable. Adapt it to your needs and capture your audience's attention.
  • 89.
    Reinforcement Learning inAI PowerPoint Presentation Slide Templates Icons Slide 89
  • 90.
    90 Additional Slides Timeline 03 Target 04 Idea Generation 05 Venn 06 Post itnotes 07 Thank you 08 Stacked Column 01 Area Chart 02
  • 91.
    Stacked Column 91 4.3 2.5 -3.5 -4.5 2.4 4.4 -1.8 -0.8 -6 -4 -2 0 2 4 6 8 Sales in million Product 02 Product 01 This graph/chartis linked to excel, and changes automatically based on data. Just left click on it and select “Edit Data”. Product 01 This graph/chart is linked to excel, and changes automatically based on data. Just left click on it and select “Edit Data”. Product 02
  • 92.
    Area Chart 92 4.3 2.5 -3.5 -4.5 2.4 4.4 -1.8 -0.8 -5 -4 -3 -2 -1 0 1 2 3 4 5 Sales in million Product02 Product 01 This graph/chart is linked to excel, and changes automatically based on data. Just left click on it and select “Edit Data”. Product 01 This graph/chart is linked to excel, and changes automatically based on data. Just left click on it and select “Edit Data”. Product 02
  • 93.
    Timeline 93 This slide is100% editable. Adapt it to your needs and capture your audience's attention. This slide is 100% editable. Adapt it to your needs and capture your audience's attention. This slide is 100% editable. Adapt it to your needs and capture your audience's attention. This slide is 100% editable. Adapt it to your needs and capture your audience's attention. This slide is 100% editable. Adapt it to your needs and capture your audience's attention. This slide is 100% editable. Adapt it to your needs and capture your audience's attention. 2015 2016 2017 2018 2019 2020
  • 94.
    Target 94 This slide is100% editable. Adapt it to your needs and capture your audience's attention. Text Here This slide is 100% editable. Adapt it to your needs and capture your audience's attention. Text Here This slide is 100% editable. Adapt it to your needs and capture your audience's attention. Text Here 01 02 03
  • 95.
    Idea Generation 95 02 04 01 03 Thisslide is 100% editable. Adapt it to your needs and capture your audience's attention. This slide is 100% editable. Adapt it to your needs and capture your audience's attention. This slide is 100% editable. Adapt it to your needs and capture your audience's attention. This slide is 100% editable. Adapt it to your needs and capture your audience's attention.
  • 96.
    Venn 96 This slide is100% editable. Adapt it to your needs and capture your audience's attention. This slide is 100% editable. Adapt it to your needs and capture your audience's attention. This slide is 100% editable. Adapt it to your needs and capture your audience's attention. This slide is 100% editable. Adapt it to your needs and capture your audience's attention. This slide is 100% editable. Adapt it to your needs and capture your audience's attention. Text Here Text Here Text Here Text Here Text Here
  • 97.
    Post It Notes 97 01 Thisslide is 100% editable. Adapt it to your needs and capture your audience's attention. 03 This slide is 100% editable. Adapt it to your needs and capture your audience's attention. 02 This slide is 100% editable. Adapt it to your needs and capture your audience's attention. 04 This slide is 100% editable. Adapt it to your needs and capture your audience's attention.
  • 98.
    Thank You 98 Call Us 0123456789 VisitUs # street number, city, state Follow Us emailaddress123@gmail.com