Hitchikers guide-to-machine-learning

•

0 likes•118 views

This talk is intended to be a fast onramp for anyone interested in becoming a machine learning practitioner. It has tips on some keys to gaining the right mix of experience and motivation.

Engineering

HITCHHIKERS GUIDETO ROCKING MACHINE
LEARNING IN 2019
Session for NewBies
Sho Fola Soboyejo
Apr 26th, 2019
@shoreason

PERSONAL APPLICATIONS
Energy utilization anomaly
detection

PERSONAL APPLICATIONS
Recommendation
Engine for nearby fun
activities

PERSONAL APPLICATIONS
Creating clusters and tiers for
fantasy football players plus
predicting performance

PERSONAL APPLICATIONS
Text Summarizer to summarize news articles

CHOOSING A PATH
What are you saying No to?

LITERACY
Learning to know
COMPETENCE
VS
Learning to Do

Amazon
ON GETTING STARTED
• Being clear where you are
starting from
• Know where you are
headed before you start

• Learning a new instrument
• Top Down = Starting with
a song
• Bottom Up = Learn A lot
ofTheory

PLAYINGTHE WHOLE GAME
• David Perkins
• Learning things on
as needed basis

WORK ONTHE HARD PARTS
• Zone of discomfort
• Circle of 5ths & Riffs
• Getting and cleaning data
• Setting up your cloud env
• Moving from Python
Notebook to CMD Line

• Fast.ai - Intro to ML Course
• Udacity ML Course
• Machine Learning is fun -
Medium Blog (Literacy)
• Deep Learning - Online book
(Literacy)
• Follow Siraj Raval, Sentdex and
Corey Schafer onYouTube

@prat0s
Neural Networks & Deep Learning
Machine Learning

FINDING A PROJECT AND
DATA
• Kaggle
• UCI ML Repository
• Fast.ai Datasets
• Your own personal project
• Hackathons

RIGHT MIX OF EXPERIENCE
AND MOTIVATION
ACHIEVING SUCCESS

FINDING MOTIVE
• Staying competitive (in your industry)
• Improving your productivity
• Being in the driver’s seat
• Managing Bias
Cranfield University Blogs

“Predictive analytics will have an effect on who
gets hired, is approved for a loan or sees an Ad”

SupportVector Machines
Random Forest
Logistic Regression
Linear Regression
K-Nearest Neighbors
K-Means Clustering
Naive Bayes Principal Component Analysis
Linear Discriminant Analysis
Neural Networks
10 AlgorithmsTo Know

Machine
Learning
“99% OF
THE ECONOMIC
VALUE LIES IN
SUPERVISED
LEARNING” Supervised
Unsupervised Clustering
Classiﬁcation
Regression

AI Fail
VS
Human Fail
ARTIFICIAL INTELLIGENCE
(OR LACK OF IT)

MORE APPLICATIONS
• Product Defect Detection Using Image Recognition
• Customer Interaction Bots
• Fraud, Anomaly and Bad Actor Detection
• Emotion Detection (Mental Health & Counseling)
• Self Driving Cars
Discover Magazine

Black Box: Sci-kit Learn Example
Credit: Adam Geitgey

Support Vector Machines
Great for
classification
problems with
numerical features
and relatively few
samples
Credit: Adedapo Alabi

Initialize: clf = svm.SVC(gamma=0.001, C=100)
Train: clf.fit(x, y)
Test: clf.score(x_test, y_test)
Predict: clf.predict(test)
Key Steps

@shoreason
www.linkedin.com/in/shofola/
github.com/shoreason

Similar to Hitchikers guide-to-machine-learning

For email marketers, fostering meaningful interactions with your subscribers is an ongoing challenge. It involves producing campaigns that have a strong impact that encourages your subscribers to act. Yet to do this, you must first understand the moments when your email message will have the most positive effect on your subscribers. This slide deck goes a long with an on-demand webinar (XXX) that uncovers eight different instances when you can strategically utilize email marketing to draw your audience in and make a big impact that creates raving fans.

8 Ways to Make a Big Impact with EMail Marketing

Pinpointe On-Demand

Showcase how machines are built to perform intelligent tasks by using our content-ready Reinforcement Learning In AI PowerPoint Presentation Slide Templates Complete Deck. Take advantage of these artificial intelligence PowerPoint visuals, and describe how machine learning models are trained to make sequences of decisions in a complex environment. Showcase the types of artificial intelligence such as deep learning, machine learning. Explain the concept of machine learning which delivers predictive models based on the data fed into machine learning algorithms. Take the assistance of our visually attention-grabbing reinforcement learning PowerPoint templates and discuss the effective uses of artificial intelligence in various areas such as supply chain, human resources, fraud detection, knowledge creation, research, and development, etc. You can also present the usage of AI in healthcare. This includes treatment, diagnosis, training and research, early detection, etc. Explain the working of machine learning by downloading our attention-grabbing supervised learning PowerPoint presentation. https://bit.ly/3kQBnEZ

Reinforcement Learning In AI Powerpoint Presentation Slide Templates Complete...

SlideTeam

Introducing Machine Learning is like opening the Pandora's Box - it unveils important issues in your data, metrics, and product. In order to deal with such complexity, pragmatic practices are required to obtain reliable results. In this talk, we will go through learnings gained from introducing Machine Learning in different contexts, from academia, start-ups, consulting to tech giants - covering practices for experimentation, infrastructure, planning, performance evaluation and product vision in the context of machine learning products.

Machine Learning: Opening the Pandora's Box - Dhiana Deva @ QCon São Paulo 2019

Dhiana Deva

Advanced Content Creation, SEO & Storytelling Here are the slides for the content marketing, SEO, storytelling, and growth hacking events that Patrick Vlaskovits and I hosted with our partners below across Europe in 2016: - Beta-i (Lisbon) - Porto Design Factory (Porto) - Founders (Copenhagen) - EIT Digital (Helsinki) - Mosaik (Budapest) We broke the events into the following 5 sections: - What really is growth hacking? - State Of The Industry - Advanced Content Marketing & Creation - Advanced SEO - Storytelling All of our examples came from personal experiences that we had not written or spoken about prior. If you have any questions, please contact me (@CaseyA - casey@fullstackmarketer.com) or Patrick (@Pv).

Advanced Content Creation, SEO & Storytelling

Casey Armstrong

Leading Edge Forums (LEF) has labelled the synergistic combination of cloud computing and machine intelligence (MI) as ‘the Matrix’: the combination of cloud services such as IaaS, IoT, MI, and edge computing. For companies to thrive, they need to know the answers to the following questions: How are successful companies harnessing the power of the Matrix? How do they structure their organizations? What makes them so agile? How do they attract and retain skilled employees? LEF studies successful businesses and learns what makes them great. Our 6-month research program has dived deep with multiple AWS customers to understand not only their use of the technology, but also the business transformation program that allowed them to maximize the value that AWS provides. Attend this session to learn more about the research that has been done, client examples, observations that the LEF has made and how this can be used to help drive your transformation program. Session sponsored by DXC Technology

How to Successfully Exploit the Power of the Matrix - ENT225 - re:Invent 2017

Amazon Web Services

KM World Enterprise Social Networking 2007

Christian Gray

How can you thrive in a future where machine learning has been popular for a few years already? In this talk, I will give you actionable advice from my experience training serious data scientists at our retreat center in Berlin. You are going to face these pointy, hard questions: - What is the promise of machine learning? Has it happened yet? - Is it easy to take advance of machine learning, now that most algorithms are nicely packaged in APIs and libraries? - How much time should I spend getting good at machine learning? Am I good enough now? - Are data scientists going to be replaced by algorithms? Are we all? - Is it easy to hire talent in machine learning after the explosion of MOOCs?

Future of data science as a profession

Jose Quesada

In small development organizations, software teams are usually able to deliver value independently of other teams. In these organizations, it is easy to give teams total autonomy. What happens as the company and systems grow to where there are multiple teams to organize and deliver value together? Usually the response from the leadership team is to align the teams, but that alignment is usually at the expense of the teams’ autonomy. How are teams supposed to be both aligned and autonomous? What is the role of leadership in both aligning the teams around a common purpose and building the environment so the teams remain autonomous? In this session we’re going to learn how to be an empowering leader who uses alignment as a pre-condition to high autonomy. We’ll learn a recipe for creating alignment and how having alignment and autonomy relates to Daniel Pink’s Autonomy, Mastery, Purpose and to David Marquet’s Leader’s Give Control models.

Inspiring Alignment and Autonomy - The Leaders Role in Scaling Agile

Leland Newsom CSP-SM, SPC5, SDP

Agile Outside Software

allan kelly

Data-driven Approach to Launching your Career

Viral Kadakia

Defining Success Metrics for World-Class Products

Product School

Siddharth Lal presents an SEO Training Masterclass for DMAasia in Delhi, India. This Search Engine Optimization presentation includes: SEO fundamentals Advanced Google Commands That Marketers Will Love The Importance of Content for ranking websites 5 Tools Data Hungry Digital Marketers Will Love. These tools will help you uncover secrets of your competitor websites. It also includes Voice Search and Vernacular Content.

SEO Training Masterclass by Siddharth Lal, Bruce Clay India for DMAasia

Sid Lal

Mastering Organic SEO by Siddharth Lal, BruceClay

Jitendra Jitu

BeaconsAI engr 245 lean launchpad stanford 2019

Stanford University

One of the most popular buzz words nowadays in the technology world is “Machine Learning (ML).” Most economists and business experts foresee Machine Learning changing every aspect of our lives in the next 10 years through automating and optimizing processes. This is leading many organizations to seek experts who can implement Machine Learning into their businesses. The paper will be written for statistical programmers who want to explore Machine Learning career, add Machine Learning skills to their experiences or enter a Machine Learning fields. The paper will discuss about personal journey to become to a Machine Learning Engineer from a statistical programmer. The paper will share my personal experience on what motivated me to start Machine Learning career, how I started it, and what I have learned and done to be a Machine Learning Engineer. In addition, the paper will also discuss the future of Machine Learning in Pharmaceutical Industry, especially in Biometric department.

How I became ML Engineer

Kevin Lee

ICWES15 - How to Get the Best for Less - Engineering Your Recruitment. Presen...

Engineers Australia

Consumer internet bbl_nov2012_gf

Maisy Samuelson

HRdergi Istanbul 2015 Good to Great: The 6 traits of High Performing Recruiters

Johnny Campbell

Measuring Relevance in the Negative Space

Trey Grainger

Cloud? DevOps? Big Data? Social? Mobile? There's a plethora of things your business should care about when competing in today's technology driven world. All of these things will be pushed onto IT as the "most important thing", but how do you manage to deliver the things your business needs in a sea of hype and buzz. Watch how Rackspace provides business platforms for you to run on and take away the mundane parts of being an IT hero.

Building Business Success from Buzz Words

Chris Jackson

Similar to Hitchikers guide-to-machine-learning (20)

8 Ways to Make a Big Impact with EMail Marketing

Reinforcement Learning In AI Powerpoint Presentation Slide Templates Complete...

Machine Learning: Opening the Pandora's Box - Dhiana Deva @ QCon São Paulo 2019

Advanced Content Creation, SEO & Storytelling

How to Successfully Exploit the Power of the Matrix - ENT225 - re:Invent 2017

KM World Enterprise Social Networking 2007

Future of data science as a profession

Inspiring Alignment and Autonomy - The Leaders Role in Scaling Agile

Agile Outside Software

Data-driven Approach to Launching your Career

Defining Success Metrics for World-Class Products

SEO Training Masterclass by Siddharth Lal, Bruce Clay India for DMAasia

Mastering Organic SEO by Siddharth Lal, BruceClay

BeaconsAI engr 245 lean launchpad stanford 2019

How I became ML Engineer

ICWES15 - How to Get the Best for Less - Engineering Your Recruitment. Presen...

Consumer internet bbl_nov2012_gf

HRdergi Istanbul 2015 Good to Great: The 6 traits of High Performing Recruiters

Measuring Relevance in the Negative Space

Building Business Success from Buzz Words

Recently uploaded

The purpose of Integrated Test Rig is to assess performance of Fuel Cooled Oil Cooler (FCOC), HP Pump & Oil Pump prior to fitment on Aero Engine. The design of rig is such that it can cater to individual testing of individual LRU or integrated testing of all the LRU’s installed together (in combination). The pumps under test shall be mounted directly on the high-speed electric motor flange through adapter quill shaft assembly. Variable speed drives shall be provided for all the pumps under testing. The rig shall cater for real time monitoring and recording of performance parameters. KEY FEATURES Key features of this Rig are as follows: - 1. It has separate power packs for both the fluids i.e. ATF Power pack for ATF Fluid, OX Power Pack for OX-27 Oil. 2. This Rig is designed for high temperature Application. It works on 200 deg. Celsius. 3. Two Dedicated heating systems have been integrated with this Rig to raise the temperature of OX-27 Oil. 4. In both Power Packs insulated tanks are being used, which is good for safe operation and safety of operator. 5. This rig is designed in such a way, that it’s OX power pack is in its left side, ATF Power pack is in right Side and test bed is in Centre. 6. A big Test bed have been provided for smooth testing of UUT’s. 7. All piping is being insulated for safe operation and maintenance. 8. It comprises with DAQ System. 9. This rig can test several components at a time, together or separately. Application All the UUT’s are mounted on HTFE-25 Engine after successful performance testing of those. Application of this Rig are as follows: - 1. One of its application is to test LP Pump of HTFE-25. It is designed for functional testing of LP Pump. a. Free Flow Test b. Load Test 2. It is used to test HP Pump of HTFE-25. It is designed for functional testing of HP Pump. a. Free Flow Test b. Load Test 3. It is used to test Oil Pump of HTFE-25. It is designed for functional testing of Oil Pump. 4. It is used to test FCOC of HTFE-25.

Integrated Test Rig For HTFE-25 - Neometrix

Neometrix_Engineering_Pvt_Ltd

S1S2 B.Arch MGU - HOA1&2 Module 3 -Temple Architecture of Kerala.pptx

SCMS School of Architecture

Theory of Time 2024 (Universal Theory for Everything)

Ramkumar k

This presentation gives you easier way to study 8086 i.e. 16 bit microprocessor. 8086 microprocessor's architecture contains two basic functional units namely Bus Interface Unit and Execution Unit. BIS fetches the instructions from memory. It reads/writes instructions to/from memory. Input/Output of data to/from I/O peripheral ports. Address generation of memory reference. Queing instructions. Thus, BIU handles all transfer of data and address. Tasks of EU: Decodes the instructions. Executes the decoded instructions. Tells BIU from where to fetch the instruction. EU takes care of performing operation on the data. EU is also known as heart of the data.

8086 Microprocessor Architecture: 16-bit microprocessor

AshwiniTodkar4

Danikor Product Catalog- Screw Feeder.pdf

thietkevietthinh

HOA1&2 - Module 3 - PREHISTORCI ARCHITECTURE OF KERALA.pptx

SCMS School of Architecture

Convergence of Robotics and Gen AI offers excellent opportunities for Entrepr...

ssuserdfc773

scipt v1.pptxcxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx...

HenryBriggs2

Adsorption (mass transfer operations 2) ppt

jigup7320

Unsatisfied Bhabhi ℂall Girls Ahmedabad Book Esha 6378878445 Top Class ℂall G...

Payal Garg #K09

Introduction to Serverless with AWS Lambda

Omar Fathy

Although the Dark web was originally used for maintaining privacy-sensitive communication for business or intelligence services for defence, government and business organizations, fighting against censorship and blocked content, later, the advantage of technologies behind the Dark web were abused by criminals to conduct crimes which involve drug dealing to the contract of assassinations in a widespread manner. Since the communication remains secure and untraceable, criminals can easily use dark web service via The Onion Router (TOR), can hide their illegal motives and can conceal their criminal activities. This makes it very difficult to monitor and detect cybercrimes over the dark web. With the evolution of machine learning, natural language processing techniques, computational big data applications and hardware, there is a growing interest in exploiting dark web data to monitor and detect criminal activities. Due to the anonymity provided by the Dark Web, the rapid disappearance and the change of the uniform resource locators (URLs) of the resources, it is not as easy to crawl the Drak web and get the data as the usual surface web which limits the researchers and law enforcement agencies to analyse the data. Therefore, there is an urgent need to study the technology behind the Dark web, its widespread abuse, its impact on society and the existing systems, to identify the sources of drug deal or terrorism activities. In this research, we analysed the predominant darker sides of the world wide web (WWW), their volumes, their contents and their ratios. We have performed the analysis of the larger malicious or hidden activities that occupy the major portions of the Dark net; tools and techniques used to identify cybercrimes which happen inside the dark web. We applied a systematic literature review (SLR) approach on the resources where the actual dark net data have been used for research purposes in several areas. From this SLR, we identified the approaches (tools and algorithms) which have been applied to analyse the Dark net data, the key gaps as well as the key contributions of the existing works in the literature. In our study, we find the main challenges to crawl the dark web and collect forum data are: scalability of crawler, content selection trade off, and social obligation for TOR crawler and the limitations of techniques used in automatic sentiment analysis to understand criminals’ forums and thereby monitor the forums. From the comprehensive analysis of existing tools, our study summarizes the most tools. However the forum topics rapidly change as their sources changes; criminals inject noises to obfuscate the forum’s main topic and thus remain undetectable. Therefore supervised techniques fail to address the above challenges. Semi-supervised techniques would be an interesting research direction.

Cybercrimes in the Darknet and Their Detections: A Comprehensive Analysis and...

dannyijwest

Fundamentals of Internet of Things (IoT) Part-2

ChandrakantDivate1

We investigated the applicability and efficiency of the MLMC approach to the Henry-like problem with uncertain porosity, permeability and recharge. These uncertain parameters were modelled by random fields with three independent random variables. Permeability is a function of porosity. Both functions are time-dependent, have multi-scale behaviour and are defined for two layers. The numerical solution for each random realisation was obtained using the well-known ug4 parallel multigrid solver. The number of random samples required at each level was estimated by calculating the decay of the variances and the computational cost for each level. The MLMC method was used to compute the expected value and variance of several QoIs, such as the solution at a few preselected points $(t,\bx)$, the solution integrated over a small subdomain, and the time evolution of the freshwater integral. We have found that some QoIs require only 2-3 mesh levels and samples from finer meshes would not significantly improve the result. Other QoIs require more grid levels.

litvinenko_Henry_Intrusion_Hong-Kong_2024.pdf

Alexander Litvinenko

Max. shear stress theory-Maximum Shear Stress Theory Maximum Distortional ...

ronahami

Robotics is an exciting and rapidly evolving field that combines engineering, computer science, and technology. Robots are versatile machines capable of automating a wide range of tasks with precision, speed, and power. This introduction will explore the history, components, and applications of this transformative technology. A robot is an electromechanical machine designed to perform tasks autonomously or semi-autonomously. Robots are controlled by sophisticated software and can be programmed to carry out a variety of functions. Robots use sensors to gather information about their environment and actuators to interact with it. The concept of automata, or self-operating machines, dates back to ancient civilizations such as Greece and China. The development of industrial machinery in the 18th and 19th centuries paved the way for modern robotics. The advent of computers in the 20th century enabled the creation of more advanced, programmable robots Industrial robots are commonly used in manufacturing, performing tasks such as welding, painting, and assembly. Service robots are designed to assist humans in tasks like cleaning, transportation, and healthcare Humanoid robots are designed to mimic the appearance and functionality of the human body. Mechanical Structure Robots have a physical frame, joints, and linkages that allow for movement and manipulation. Power Source Robots require a power source, such as batteries or electrical connections, to operate. Control System The control system, often a computer or microcontroller, coordinates the robot's actions and movements End Effectors Robots may have specialized tools, such as grippers or tools, to interact with their environment Cameras and other vision sensors allow robots to perceive and respond to their environment. Ultrasonic and infrared sensors help robots detect and avoid obstacles. Tactile sensors enable robots to feel and interact with their surroundings. Motors, servos, and other actuators allow robots to move and manipulate objects. Robots are controlled by sophisticated software that defines their behaviors and decision-making processes. Algorithms enable robots to process sensor data, plan actions, and execute tasks autonomously. Advancements in machine learning allow robots to adapt and improve their performance over time. Applications of Robotics Robots are widely used in industrial settings for tasks such as assembly, welding, and packaging. Robotic systems are revolutionizing medicine, from surgical assistants to rehabilitation devices. Robots are essential for exploring hazardous environments, such as deep-sea and outer space

Introduction to Robotics in Mechanical Engineering.pptx

hublikarsn

Online Food Ordering System is proposed for simplifies the food ordering process. ThisSystem shows an user interface and update the menu with all available options so that it eases thecustomer work. Customer can choose more than one item to make an order and can view Orderdetails before logging off. The order confirmation is sent to the customer. The order is placed inthe queue and updated in the Database and returned in real time. This system assists the staff togo through the orders in real time and process it efficiently. Online food order system is mainlydesigned primarily function for use in the food delivery industry. This system will allowhotels and restaurants to increase online food ordering such type of business. The customerscan be selected food menu items just few minutes. In the modern food industries allows toquickly and easily delivery on customer place. Restaurant employees then use these ordersthrough an easy to delivery on customer place easy find out navigate graphical interface forefficient processing .

Online food ordering system project report.pdf

Kamal Acharya

POST OFFICE works in every walk of our life. Through the automation of this system one can easily generate the information about the customer available and also about the old records. For this efficient software the first and the foremost thing is that all the requirements should be known before hand and the developer should devote its effort for the completion of that requirement which are demanded by the customer should be fulfilled. This system can be used in various education departments and can distribute the copies of the system among the management and staff members for the required information of their customer.

Post office management system project ..pdf

Kamal Acharya

Worksharing and 3D Modeling with Revit.pptx

Mustafa Ahmed

The project Hospital Management system includes registration of patients, storing their details into the system, and also computerized billing in the pharmacy, and labs. The software has the facility to give a unique id for every patient and stores the details of every patient and the staff automatically. It includes a search facility to know the current status of each room. User can search availability of a doctor and the details of a patient using the id. The Hospital Management System can be entered using a username and password. It is accessible either by an administrator or receptionist. Only they can add data into the database. The data can be retrieved easily. The interface is very user-friendly. The data are well protected for personal use and makes the data processing very fast. Hospital Management System is powerful, flexible, and easy to use and is designed and developed to deliver real conceivable benefits to hospitals. Hospital Management System is designed for multispecialty hospitals, to cover a wide range of hospital administration and management processes. It is an integrated end-to-end Hospital Management System that provides relevant information across the hospital to support effective decision making for patient care, hospital administration and critical financial accounting, in a seamless flow. Hospital Management System is a software product suite designed to improve the quality and management of hospital management in the areas of clinical process analysis and activity-based costing. Hospital Management System enables you to develop your organization and improve its effectiveness and quality of work. Managing the key processes efficiently is critical to the success of the hospital helps you manage your processes.

Hospital management system project report.pdf

Kamal Acharya

Recently uploaded (20)

Integrated Test Rig For HTFE-25 - Neometrix

S1S2 B.Arch MGU - HOA1&2 Module 3 -Temple Architecture of Kerala.pptx

Theory of Time 2024 (Universal Theory for Everything)

8086 Microprocessor Architecture: 16-bit microprocessor

Danikor Product Catalog- Screw Feeder.pdf

HOA1&2 - Module 3 - PREHISTORCI ARCHITECTURE OF KERALA.pptx

Convergence of Robotics and Gen AI offers excellent opportunities for Entrepr...

scipt v1.pptxcxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx...

Adsorption (mass transfer operations 2) ppt

Unsatisfied Bhabhi ℂall Girls Ahmedabad Book Esha 6378878445 Top Class ℂall G...

Introduction to Serverless with AWS Lambda

Cybercrimes in the Darknet and Their Detections: A Comprehensive Analysis and...

Fundamentals of Internet of Things (IoT) Part-2

litvinenko_Henry_Intrusion_Hong-Kong_2024.pdf

Max. shear stress theory-Maximum Shear Stress Theory Maximum Distortional ...

Introduction to Robotics in Mechanical Engineering.pptx

Online food ordering system project report.pdf

Post office management system project ..pdf

Worksharing and 3D Modeling with Revit.pptx

Hospital management system project report.pdf

Hitchikers guide-to-machine-learning

1. HITCHHIKERS GUIDETO ROCKING MACHINE LEARNING IN 2019 Session for NewBies Sho Fola Soboyejo Apr 26th, 2019 @shoreason

2. 10,000hours

3. Photo by: Douglas Adams

4. PERSONAL APPLICATIONS Energy utilization anomaly detection

5. PERSONAL APPLICATIONS Recommendation Engine for nearby fun activities

6. PERSONAL APPLICATIONS Creating clusters and tiers for fantasy football players plus predicting performance

7. PERSONAL APPLICATIONS Text Summarizer to summarize news articles

8. 80/20Rule

9. CHOOSING A PATH What are you saying No to?

10. LITERACY Learning to know COMPETENCE VS Learning to Do

11. Amazon ON GETTING STARTED • Being clear where you are starting from • Know where you are headed before you start

12. ISTHISYOU?

13. • Learning a new instrument • Top Down = Starting with a song • Bottom Up = Learn A lot ofTheory

14. PLAYINGTHE WHOLE GAME • David Perkins • Learning things on as needed basis

15. WORK ONTHE HARD PARTS • Zone of discomfort • Circle of 5ths & Riffs • Getting and cleaning data • Setting up your cloud env • Moving from Python Notebook to CMD Line

16. RESOURCES

17. • Fast.ai - Intro to ML Course • Udacity ML Course • Machine Learning is fun - Medium Blog (Literacy) • Deep Learning - Online book (Literacy) • Follow Siraj Raval, Sentdex and Corey Schafer onYouTube

18. LANGUAGES VS TOOLS

19. @prat0s Neural Networks & Deep Learning Machine Learning

20. PLATFORMS

21. FINDING A PROJECT AND DATA • Kaggle • UCI ML Repository • Fast.ai Datasets • Your own personal project • Hackathons

22. RIGHT MIX OF EXPERIENCE AND MOTIVATION ACHIEVING SUCCESS

23. FINDING MOTIVE • Staying competitive (in your industry) • Improving your productivity • Being in the driver’s seat • Managing Bias Cranfield University Blogs

24.

25. FINDING MOTIVE • Staying competitive (in your industry) • Improving your productivity • Being in the driver’s seat • Managing Bias Cranfield University Blogs

26.

27. FINDING MOTIVE • Staying competitive (in your industry) • Improving your productivity • Being in the driver’s seat • Managing Bias Cranfield University Blogs

28. “Predictive analytics will have an effect on who gets hired, is approved for a loan or sees an Ad”

29. FINDING MOTIVE • Staying competitive (in your industry) • Improving your productivity • Being in the driver’s seat • Managing Bias Cranfield University Blogs

30.

31.

32. TheTimeline Nvidia

33. SupportVector Machines Random Forest Logistic Regression Linear Regression K-Nearest Neighbors K-Means Clustering Naive Bayes Principal Component Analysis Linear Discriminant Analysis Neural Networks 10 AlgorithmsTo Know

34. Machine Learning “99% OF THE ECONOMIC VALUE LIES IN SUPERVISED LEARNING” Supervised Unsupervised Clustering Classiﬁcation Regression

35. Photo by: Douglas Adams

36.

37. AI Fail VS Human Fail ARTIFICIAL INTELLIGENCE (OR LACK OF IT)

38. MORE APPLICATIONS • Product Defect Detection Using Image Recognition • Customer Interaction Bots • Fraud, Anomaly and Bad Actor Detection • Emotion Detection (Mental Health & Counseling) • Self Driving Cars Discover Magazine

39. Literacy

40. Competency

41. HANDS-ON TIME

42. Black Box: Sci-kit Learn Example Credit: Adam Geitgey

43. Support Vector Machines Great for classification problems with numerical features and relatively few samples Credit: Adedapo Alabi

44. Initialize: clf = svm.SVC(gamma=0.001, C=100) Train: clf.fit(x, y) Test: clf.score(x_test, y_test) Predict: clf.predict(test) Key Steps

45. Scikit Learn Example

46. Photo by: Douglas Adams DECEMBER 2019

47. DECEMBER 2019

48. @shoreason www.linkedin.com/in/shofola/ github.com/shoreason