SlideShare a Scribd company logo
WELCOME TO:
Deep Learning AI Technologies
1. Neural Networks
2. CNN
By Adj Prof. Giuseppe Mascarella
giuseppe@valueamplify.com
https://docs.microsoft.com/en
-us/azure/machine-
learning/concept-deep-
learning-vs-machine-
learning?WT.mc_id=wiley-
book-lazzeri
(Incl Heuristic)
Stochastic Gradient Descent for Bayesian
Neural Networks
DEFINITIONS
A) BAYESIAN
Bayesian inference is a method of statistical inference in which Bayes'
theorem is used to update the probability for a hypothesis as more evidence
or information becomes available.
B) Heuristic
Experimenting, evaluating possible answers or solutions, or by trial and
error
Shortcuts to make decisions based on past events or traits that are
representative of or similar to the current situation.
Heuristics in
Neural Networks
What Is a Neural Network”
A is a set of interconnected layers.
The inputs are the first layer, and are connected to an output layer by
an acyclic graph comprised of weighted edges and nodes.
A NN is a DNN (Deep Neural Networks) when you have many hidden
layers has more accuracy.
All nodes in a layer are connected by the weighted edges to nodes in
the next layer.
To compute the output of the network for a particular input, the value
is set by calculating the weighted sum of the values of the nodes from
the previous layer.
An activation function is then applied to that weighted sum.
Neural Networks Basics
X1 - Is the weather good?
X2 - Does your boyfriend or girlfriend want
to accompany you?
X3 - Is the festival near public transit?
(You don't own a car).
The artificial
neuron are
called:
perceptron
• w1=6 for the weather
• w2=2
• w3=2 for the other
conditions.
• Threshold
(Bias Toward
Cheese)= 3
Biz Problem To Solve: Predict, Will John Go To The Cheese Festival This Weekend?
W=> Tool for a device that
makes decisions by weighing
up evidence and previous
results.
NAND Electrical Circuit Operator
0,1
Bias: how easy it is to get
the perceptron to fire
W
3
Sigmoid Neuron
• Learning algorithms which can
automatically tune neurons:
• Weights
• biases
8 vs 9
=
=
Backpropagation! The algo that computes the best Gradient
Cost Function: MSE (Mean Squared Error)
n is the total number of training inputs,
a is the vector of outputs from the network w/x as input
Sum is over all training inputs, x
Y=(m n +x)
C = w2-w1/(y2-y1)
Gradient Descent Function
How To Configure a NN (Part 1)
https://docs.microsoft.com/en-us/azure/machine-learning/studio-module-reference/two-class-neural-network
1. Category
2. Parameters (Hyperparameters)
3. Hidden Layers
4. Hidden Nodes, default in a hidden layer is 100 nodes.
5. Learning rate, define the size of the step taken at each iteration,
before correction. (i.e. a larger value for learning rate can cause the model to
converge faster, but it can overshoot local minima.)
6. Number of learning iterations, specify the maximum number of
times the algorithm should process the training cases.
7. Initial Learning Weights Diameter, specify the node weights at
the start of the learning process.
8. Momentum, specify a weight to apply during learning to nodes
from previous iterations.
https://distill.pub/2017/momentum/
Scripted, custom CNN
input Picture [28, 28];
hidden C1 [5, 12, 12]
from Picture convolve {
InputShape = [28, 28];
KernelShape = [ 5, 5];
Stride = [ 2, 2];
MapCount = 5;
}
How To Configure a NN (Part 2)
• Type of normalizer, select a method to use for feature normalization. The following normalization methods are
supported:
• Binning normalizer: The binning normalizer creates bins of equal size, and then normalizes every value in each bin,
dividing by the total number of bins.
• Gaussian normalizer: The Gaussian normalizer rescales the values of each feature to have mean 0 and variance 1. This is
done by computing the mean and the variance of each feature. For each instance, the mean value is subtracted, and the
result divided by the square root of the variance (the standard deviation).
• Min-max normalizer: The min-max normalizer linearly rescales every feature to the [0,1] interval.Rescaling to the [0,1]
interval is done by shifting the values of each feature so that the minimal value is 0, and then dividing by the new maximal
value (which is the difference between the original maximal and minimal values).
• Do not normalize: No normalization is performed.
• Shuffle examples option to shuffle cases between iterations. If you deselect this option, cases are processed in
exactly the same order each time you run the experiment.
• Random number seed, type a value to use as the seed. Specifying a seed value is useful when you want to
ensure repeatability across runs of the same experiment. Otherwise, a system clock value is used as the seed,
which can cause slightly different results each time you run the experiment.
• Allow unknown categorical levels option to create a grouping for unknown values in the training and
validation sets. The model might be less precise on known values but provide better predictions for new
(unknown) values. If you deselect this option, the model can accept only the values contained in the training
data.
NN
Configuration
Summary
Tune Model Hyperparameters
• Integrated train and tune: You configure a set of
parameters to use, and then let the module iterate over
multiple combinations, measuring accuracy until it finds a
"best" model. With most learner modules, you can choose
which parameters should be changed during the training
process, and which should remain fixed.
•Depending on how long you want the tuning process to
run, you might decide to exhaustively test all
combinations, or you could shorten the process by
establishing a grid of parameter combinations and testing
a randomized subset of the parameter grid.
• Cross validation with tuning: With this option, you
divide your data into some number of folds and then build
and test models on each fold. This method provides the
best accuracy and can help find problems with the dataset;
however, it takes longer to train.
Assignment: NN ML Experiment Reverse
Engineering
• https://gallery.azure.ai/Experiment/pranab-p181a35-nlp-final-exam
WELCOME TO:
Deep Learning AI Technologies
1. Neural Networks
2. CNN(Convoluted Networks)
By Adj Prof. Giuseppe Mascarella
giuseppe@valueamplify.com
CNN Definitions
A. Inspired by biological processes[7][8][9][10] in that
the connectivity pattern between neurons resembles the organization of the animal visual
cortex.
Individual cortical neurons respond to stimuli only in a restricted region of the visual field known
as the receptive field. The receptive fields of different neurons partially overlap such that they
cover the entire visual field.
B. The name “convolutional neural network” indicates that the network employs a mathematical
operation called convolution that is a mathematical operation on two functions (f and g) that
produces a third function (f*g) expressing how the shape of one is modified by the other.
C. The convolutional layer is the core building block of a CNN. The layer's parameters
consist of a set of learnable filters (or kernels), which have a small receptive field, but
extend through the full depth of the input volume.
D. They are also known as shift invariant or space invariant artificial neural networks
(SIANN), based on their shared-weights architecture and translation invariance
characteristics.
CNN
Applications:
image and video recognition, recommender systems, image
classification, medical image analysis, natural language processing, and
financial time series.
WHY?
CNNs use relatively little pre-processing compared to other image
classification algorithms.
This means that the network learns the filters that in traditional algorithms
were hand-engineered. This independence from prior knowledge and human effort
in feature design is a major advantage.
What Problem Is CNN Trying To Solve?
Adaptation for education purpose from: https://www.youtube.com/watch?v=2-Ol7ZB0MmU
CNN Deep Learning Is a Brilliant A Series Of
Classifiers Orchestrated in Layers
CNN Architecture
Derivative work from: A friendly introduction to Convolutional Neural Networks and Image Recognition by
Serrano
Apply Filter
Pooling Layer
Compare
Convolution Network
Create Random Numbers And Gradient Descend
CNN
LSTM (Long short-term memory) Algo
Long short-term memory (LSTM) is an artificial recurrent neural
network (RNN) architecture used in the field of deep learning. Unlike
standard feedforward neural networks, LSTM has feedback
connections.
• The aim of predictive maintenance (PdM) is first to predict when
equipment failure might occur, and secondly, to prevent the occurrence of
the failure by performing maintenance. ... When predictive maintenance is
working effectively as a maintenance strategy, maintenance is only
performed on machines when it is required.
• The asset of interest has a progressing degradation pattern, which is
reflected in the asset's sensor measurements." Some FMEA shows that
assets fail without a detectable degradation pattern. Also, sensor
(performance) data is only one piece of the picture. Asset configuration will
impact RUL also. If I swap an old fan blade (or a non-OEM fan blade, etc.)
into my engine, it will alter RUL. If the model doesn't know how many
cycles the fan blade has on it, it will break.

More Related Content

What's hot

Neural network
Neural networkNeural network
Neural network
Babu Priyavrat
 
Neural Networks in Data Mining - “An Overview”
Neural Networks  in Data Mining -   “An Overview”Neural Networks  in Data Mining -   “An Overview”
Neural Networks in Data Mining - “An Overview”
Dr.(Mrs).Gethsiyal Augasta
 
Artificial Neural Network and its Applications
Artificial Neural Network and its ApplicationsArtificial Neural Network and its Applications
Artificial Neural Network and its Applications
shritosh kumar
 
Deep Learning With Neural Networks
Deep Learning With Neural NetworksDeep Learning With Neural Networks
Deep Learning With Neural Networks
Aniket Maurya
 
Artificial Neural Network
Artificial Neural NetworkArtificial Neural Network
Artificial Neural Network
Burhan Muzafar
 
Designing your neural networks – a step by step walkthrough
Designing your neural networks – a step by step walkthroughDesigning your neural networks – a step by step walkthrough
Designing your neural networks – a step by step walkthrough
Lavanya Shukla
 
Neural network
Neural network Neural network
Neural network
Faireen
 
Intro to Neural Networks
Intro to Neural NetworksIntro to Neural Networks
Intro to Neural Networks
Dean Wyatte
 
Perceptron & Neural Networks
Perceptron & Neural NetworksPerceptron & Neural Networks
Perceptron & Neural Networks
NAGUR SHAREEF SHAIK
 
Neurally Controlled Robot That Learns
Neurally Controlled Robot That LearnsNeurally Controlled Robot That Learns
Neurally Controlled Robot That Learns
Benjamin Walther Büel
 
mohsin dalvi artificial neural networks presentation
mohsin dalvi   artificial neural networks presentationmohsin dalvi   artificial neural networks presentation
mohsin dalvi artificial neural networks presentation
Akash Maurya
 
Tamil Character Recognition based on Back Propagation Neural Networks
Tamil Character Recognition based on Back Propagation Neural NetworksTamil Character Recognition based on Back Propagation Neural Networks
Tamil Character Recognition based on Back Propagation Neural Networks
DR.P.S.JAGADEESH KUMAR
 
Neural network & its applications
Neural network & its applications Neural network & its applications
Neural network & its applications
Ahmed_hashmi
 
Artificial intelligence NEURAL NETWORKS
Artificial intelligence NEURAL NETWORKSArtificial intelligence NEURAL NETWORKS
Artificial intelligence NEURAL NETWORKS
REHMAT ULLAH
 
Artificial Neural Network
Artificial Neural NetworkArtificial Neural Network
Artificial Neural Network
Dessy Amirudin
 
NEURAL Network Design Training
NEURAL Network Design  TrainingNEURAL Network Design  Training
NEURAL Network Design TrainingESCOM
 
Artificial Neural Network.pptx
Artificial Neural Network.pptxArtificial Neural Network.pptx
Artificial Neural Network.pptx
ASHUTOSHMISHRA720383
 
Project presentation
Project presentationProject presentation
Project presentation
Madhv Kushawah
 
Deep learning
Deep learningDeep learning
Deep learning
Ratnakar Pandey
 
Neural Networks: Introducton
Neural Networks: IntroductonNeural Networks: Introducton
Neural Networks: Introducton
Mostafa G. M. Mostafa
 

What's hot (20)

Neural network
Neural networkNeural network
Neural network
 
Neural Networks in Data Mining - “An Overview”
Neural Networks  in Data Mining -   “An Overview”Neural Networks  in Data Mining -   “An Overview”
Neural Networks in Data Mining - “An Overview”
 
Artificial Neural Network and its Applications
Artificial Neural Network and its ApplicationsArtificial Neural Network and its Applications
Artificial Neural Network and its Applications
 
Deep Learning With Neural Networks
Deep Learning With Neural NetworksDeep Learning With Neural Networks
Deep Learning With Neural Networks
 
Artificial Neural Network
Artificial Neural NetworkArtificial Neural Network
Artificial Neural Network
 
Designing your neural networks – a step by step walkthrough
Designing your neural networks – a step by step walkthroughDesigning your neural networks – a step by step walkthrough
Designing your neural networks – a step by step walkthrough
 
Neural network
Neural network Neural network
Neural network
 
Intro to Neural Networks
Intro to Neural NetworksIntro to Neural Networks
Intro to Neural Networks
 
Perceptron & Neural Networks
Perceptron & Neural NetworksPerceptron & Neural Networks
Perceptron & Neural Networks
 
Neurally Controlled Robot That Learns
Neurally Controlled Robot That LearnsNeurally Controlled Robot That Learns
Neurally Controlled Robot That Learns
 
mohsin dalvi artificial neural networks presentation
mohsin dalvi   artificial neural networks presentationmohsin dalvi   artificial neural networks presentation
mohsin dalvi artificial neural networks presentation
 
Tamil Character Recognition based on Back Propagation Neural Networks
Tamil Character Recognition based on Back Propagation Neural NetworksTamil Character Recognition based on Back Propagation Neural Networks
Tamil Character Recognition based on Back Propagation Neural Networks
 
Neural network & its applications
Neural network & its applications Neural network & its applications
Neural network & its applications
 
Artificial intelligence NEURAL NETWORKS
Artificial intelligence NEURAL NETWORKSArtificial intelligence NEURAL NETWORKS
Artificial intelligence NEURAL NETWORKS
 
Artificial Neural Network
Artificial Neural NetworkArtificial Neural Network
Artificial Neural Network
 
NEURAL Network Design Training
NEURAL Network Design  TrainingNEURAL Network Design  Training
NEURAL Network Design Training
 
Artificial Neural Network.pptx
Artificial Neural Network.pptxArtificial Neural Network.pptx
Artificial Neural Network.pptx
 
Project presentation
Project presentationProject presentation
Project presentation
 
Deep learning
Deep learningDeep learning
Deep learning
 
Neural Networks: Introducton
Neural Networks: IntroductonNeural Networks: Introducton
Neural Networks: Introducton
 

Similar to AI Class Topic 6: Easy Way to Learn Deep Learning AI Technologies

ML Module 3 Non Linear Learning.pptx
ML Module 3 Non Linear Learning.pptxML Module 3 Non Linear Learning.pptx
ML Module 3 Non Linear Learning.pptx
DebabrataPain1
 
IRJET-Breast Cancer Detection using Convolution Neural Network
IRJET-Breast Cancer Detection using Convolution Neural NetworkIRJET-Breast Cancer Detection using Convolution Neural Network
IRJET-Breast Cancer Detection using Convolution Neural Network
IRJET Journal
 
Hands on machine learning with scikit-learn and tensor flow by ahmed yousry
Hands on machine learning with scikit-learn and tensor flow by ahmed yousryHands on machine learning with scikit-learn and tensor flow by ahmed yousry
Hands on machine learning with scikit-learn and tensor flow by ahmed yousry
Ahmed Yousry
 
Deep learning from a novice perspective
Deep learning from a novice perspectiveDeep learning from a novice perspective
Deep learning from a novice perspective
Anirban Santara
 
deeplearning
deeplearningdeeplearning
deeplearning
huda2018
 
SoftComputing6
SoftComputing6SoftComputing6
SoftComputing6
DrPrafullNarooka
 
Facial Emotion Detection on Children's Emotional Face
Facial Emotion Detection on Children's Emotional FaceFacial Emotion Detection on Children's Emotional Face
Facial Emotion Detection on Children's Emotional Face
Takrim Ul Islam Laskar
 
Recent advances of AI for medical imaging : Engineering perspectives
Recent advances of AI for medical imaging : Engineering perspectivesRecent advances of AI for medical imaging : Engineering perspectives
Recent advances of AI for medical imaging : Engineering perspectives
Namkug Kim
 
Deep Learning with Apache MXNet (September 2017)
Deep Learning with Apache MXNet (September 2017)Deep Learning with Apache MXNet (September 2017)
Deep Learning with Apache MXNet (September 2017)
Julien SIMON
 
Ann model and its application
Ann model and its applicationAnn model and its application
Ann model and its application
milan107
 
Neural networks and deep learning
Neural networks and deep learningNeural networks and deep learning
Neural networks and deep learning
RADO7900
 
Deep Learning: concepts and use cases (October 2018)
Deep Learning: concepts and use cases (October 2018)Deep Learning: concepts and use cases (October 2018)
Deep Learning: concepts and use cases (October 2018)
Julien SIMON
 
Terminology Machine Learning
Terminology Machine LearningTerminology Machine Learning
Terminology Machine Learning
DataminingTools Inc
 
DEF CON 24 - Clarence Chio - machine duping 101
DEF CON 24 - Clarence Chio - machine duping 101DEF CON 24 - Clarence Chio - machine duping 101
DEF CON 24 - Clarence Chio - machine duping 101
Felipe Prado
 
neuralnetwork.pptx
neuralnetwork.pptxneuralnetwork.pptx
neuralnetwork.pptx
Karthik Rohan
 
Separating Hype from Reality in Deep Learning with Sameer Farooqui
 Separating Hype from Reality in Deep Learning with Sameer Farooqui Separating Hype from Reality in Deep Learning with Sameer Farooqui
Separating Hype from Reality in Deep Learning with Sameer Farooqui
Databricks
 
Artificial Neural networks
Artificial Neural networksArtificial Neural networks
Artificial Neural networks
Learnbay Datascience
 
Deep learning
Deep learningDeep learning
Deep learning
Aman Kamboj
 

Similar to AI Class Topic 6: Easy Way to Learn Deep Learning AI Technologies (20)

ML Module 3 Non Linear Learning.pptx
ML Module 3 Non Linear Learning.pptxML Module 3 Non Linear Learning.pptx
ML Module 3 Non Linear Learning.pptx
 
IRJET-Breast Cancer Detection using Convolution Neural Network
IRJET-Breast Cancer Detection using Convolution Neural NetworkIRJET-Breast Cancer Detection using Convolution Neural Network
IRJET-Breast Cancer Detection using Convolution Neural Network
 
Hands on machine learning with scikit-learn and tensor flow by ahmed yousry
Hands on machine learning with scikit-learn and tensor flow by ahmed yousryHands on machine learning with scikit-learn and tensor flow by ahmed yousry
Hands on machine learning with scikit-learn and tensor flow by ahmed yousry
 
Deep learning from a novice perspective
Deep learning from a novice perspectiveDeep learning from a novice perspective
Deep learning from a novice perspective
 
deeplearning
deeplearningdeeplearning
deeplearning
 
SoftComputing6
SoftComputing6SoftComputing6
SoftComputing6
 
Facial Emotion Detection on Children's Emotional Face
Facial Emotion Detection on Children's Emotional FaceFacial Emotion Detection on Children's Emotional Face
Facial Emotion Detection on Children's Emotional Face
 
Recent advances of AI for medical imaging : Engineering perspectives
Recent advances of AI for medical imaging : Engineering perspectivesRecent advances of AI for medical imaging : Engineering perspectives
Recent advances of AI for medical imaging : Engineering perspectives
 
PNN and inversion-B
PNN and inversion-BPNN and inversion-B
PNN and inversion-B
 
Deep Learning with Apache MXNet (September 2017)
Deep Learning with Apache MXNet (September 2017)Deep Learning with Apache MXNet (September 2017)
Deep Learning with Apache MXNet (September 2017)
 
Ann model and its application
Ann model and its applicationAnn model and its application
Ann model and its application
 
Neural networks and deep learning
Neural networks and deep learningNeural networks and deep learning
Neural networks and deep learning
 
Deep Learning: concepts and use cases (October 2018)
Deep Learning: concepts and use cases (October 2018)Deep Learning: concepts and use cases (October 2018)
Deep Learning: concepts and use cases (October 2018)
 
Terminology Machine Learning
Terminology Machine LearningTerminology Machine Learning
Terminology Machine Learning
 
N ns 1
N ns 1N ns 1
N ns 1
 
DEF CON 24 - Clarence Chio - machine duping 101
DEF CON 24 - Clarence Chio - machine duping 101DEF CON 24 - Clarence Chio - machine duping 101
DEF CON 24 - Clarence Chio - machine duping 101
 
neuralnetwork.pptx
neuralnetwork.pptxneuralnetwork.pptx
neuralnetwork.pptx
 
Separating Hype from Reality in Deep Learning with Sameer Farooqui
 Separating Hype from Reality in Deep Learning with Sameer Farooqui Separating Hype from Reality in Deep Learning with Sameer Farooqui
Separating Hype from Reality in Deep Learning with Sameer Farooqui
 
Artificial Neural networks
Artificial Neural networksArtificial Neural networks
Artificial Neural networks
 
Deep learning
Deep learningDeep learning
Deep learning
 

More from Value Amplify Consulting

AI Is An ROI Booster For Restaurants
AI Is An ROI Booster For RestaurantsAI Is An ROI Booster For Restaurants
AI Is An ROI Booster For Restaurants
Value Amplify Consulting
 
AI Class Topic 5: Social Network Graph
AI Class Topic 5:  Social Network GraphAI Class Topic 5:  Social Network Graph
AI Class Topic 5: Social Network Graph
Value Amplify Consulting
 
AI Class Topic 4: Text Analytics, Sentiment Analysis and Apache Spark
AI Class Topic 4: Text Analytics, Sentiment Analysis and Apache SparkAI Class Topic 4: Text Analytics, Sentiment Analysis and Apache Spark
AI Class Topic 4: Text Analytics, Sentiment Analysis and Apache Spark
Value Amplify Consulting
 
AI Class Topic 3: Building Machine Learning Predictive Systems (Predictive Ma...
AI Class Topic 3: Building Machine Learning Predictive Systems (Predictive Ma...AI Class Topic 3: Building Machine Learning Predictive Systems (Predictive Ma...
AI Class Topic 3: Building Machine Learning Predictive Systems (Predictive Ma...
Value Amplify Consulting
 
AI Class Topic 2: Step-by-step Process for AI development
AI Class Topic 2: Step-by-step Process for AI developmentAI Class Topic 2: Step-by-step Process for AI development
AI Class Topic 2: Step-by-step Process for AI development
Value Amplify Consulting
 
What Is Artificial Intelligence? Part 1/10
What Is Artificial Intelligence? Part 1/10What Is Artificial Intelligence? Part 1/10
What Is Artificial Intelligence? Part 1/10
Value Amplify Consulting
 
Fractional Chief AI Officer Services For Hire
Fractional Chief AI Officer Services For HireFractional Chief AI Officer Services For Hire
Fractional Chief AI Officer Services For Hire
Value Amplify Consulting
 
Chief AI Officer and AI Digital Transformation
Chief AI Officer and AI Digital TransformationChief AI Officer and AI Digital Transformation
Chief AI Officer and AI Digital Transformation
Value Amplify Consulting
 
AI Planning Workshop overview
AI Planning Workshop overviewAI Planning Workshop overview
AI Planning Workshop overview
Value Amplify Consulting
 
EKATRA IoT Digital Twin Presentation at FOG World Congress
EKATRA IoT Digital Twin Presentation at FOG World Congress EKATRA IoT Digital Twin Presentation at FOG World Congress
EKATRA IoT Digital Twin Presentation at FOG World Congress
Value Amplify Consulting
 
EKATRA IoT Digital Twin Presentation at FOG World Congress
EKATRA IoT Digital Twin Presentation at FOG World CongressEKATRA IoT Digital Twin Presentation at FOG World Congress
EKATRA IoT Digital Twin Presentation at FOG World Congress
Value Amplify Consulting
 
AI WITH AN ROI
AI WITH AN ROIAI WITH AN ROI
AI WITH AN ROI
Value Amplify Consulting
 
Bitcoin, Altcoins and Trading Robots jan2018
Bitcoin, Altcoins  and Trading Robots jan2018Bitcoin, Altcoins  and Trading Robots jan2018
Bitcoin, Altcoins and Trading Robots jan2018
Value Amplify Consulting
 
Bitcoin and Blockchain overview
Bitcoin and Blockchain overviewBitcoin and Blockchain overview
Bitcoin and Blockchain overview
Value Amplify Consulting
 
Bitcoin: Busienss and Technology Robot Overview
Bitcoin: Busienss and Technology Robot OverviewBitcoin: Busienss and Technology Robot Overview
Bitcoin: Busienss and Technology Robot Overview
Value Amplify Consulting
 
ICOs Good The Bad and the Ugly
ICOs Good The Bad and the UglyICOs Good The Bad and the Ugly
ICOs Good The Bad and the Ugly
Value Amplify Consulting
 
Tutorial on BlockChain and ICO in Commodity Trading
Tutorial on BlockChain and ICO in Commodity TradingTutorial on BlockChain and ICO in Commodity Trading
Tutorial on BlockChain and ICO in Commodity Trading
Value Amplify Consulting
 
Introduction to Blockchain and BitCoin New Business Opportunties
Introduction to Blockchain and BitCoin New Business OpportuntiesIntroduction to Blockchain and BitCoin New Business Opportunties
Introduction to Blockchain and BitCoin New Business Opportunties
Value Amplify Consulting
 
Rapid Economic Justifcation for Machine Learning in IoT
Rapid Economic Justifcation for Machine Learning in IoTRapid Economic Justifcation for Machine Learning in IoT
Rapid Economic Justifcation for Machine Learning in IoT
Value Amplify Consulting
 
ROI of Machine Learning In IoT
ROI of Machine Learning In IoTROI of Machine Learning In IoT
ROI of Machine Learning In IoT
Value Amplify Consulting
 

More from Value Amplify Consulting (20)

AI Is An ROI Booster For Restaurants
AI Is An ROI Booster For RestaurantsAI Is An ROI Booster For Restaurants
AI Is An ROI Booster For Restaurants
 
AI Class Topic 5: Social Network Graph
AI Class Topic 5:  Social Network GraphAI Class Topic 5:  Social Network Graph
AI Class Topic 5: Social Network Graph
 
AI Class Topic 4: Text Analytics, Sentiment Analysis and Apache Spark
AI Class Topic 4: Text Analytics, Sentiment Analysis and Apache SparkAI Class Topic 4: Text Analytics, Sentiment Analysis and Apache Spark
AI Class Topic 4: Text Analytics, Sentiment Analysis and Apache Spark
 
AI Class Topic 3: Building Machine Learning Predictive Systems (Predictive Ma...
AI Class Topic 3: Building Machine Learning Predictive Systems (Predictive Ma...AI Class Topic 3: Building Machine Learning Predictive Systems (Predictive Ma...
AI Class Topic 3: Building Machine Learning Predictive Systems (Predictive Ma...
 
AI Class Topic 2: Step-by-step Process for AI development
AI Class Topic 2: Step-by-step Process for AI developmentAI Class Topic 2: Step-by-step Process for AI development
AI Class Topic 2: Step-by-step Process for AI development
 
What Is Artificial Intelligence? Part 1/10
What Is Artificial Intelligence? Part 1/10What Is Artificial Intelligence? Part 1/10
What Is Artificial Intelligence? Part 1/10
 
Fractional Chief AI Officer Services For Hire
Fractional Chief AI Officer Services For HireFractional Chief AI Officer Services For Hire
Fractional Chief AI Officer Services For Hire
 
Chief AI Officer and AI Digital Transformation
Chief AI Officer and AI Digital TransformationChief AI Officer and AI Digital Transformation
Chief AI Officer and AI Digital Transformation
 
AI Planning Workshop overview
AI Planning Workshop overviewAI Planning Workshop overview
AI Planning Workshop overview
 
EKATRA IoT Digital Twin Presentation at FOG World Congress
EKATRA IoT Digital Twin Presentation at FOG World Congress EKATRA IoT Digital Twin Presentation at FOG World Congress
EKATRA IoT Digital Twin Presentation at FOG World Congress
 
EKATRA IoT Digital Twin Presentation at FOG World Congress
EKATRA IoT Digital Twin Presentation at FOG World CongressEKATRA IoT Digital Twin Presentation at FOG World Congress
EKATRA IoT Digital Twin Presentation at FOG World Congress
 
AI WITH AN ROI
AI WITH AN ROIAI WITH AN ROI
AI WITH AN ROI
 
Bitcoin, Altcoins and Trading Robots jan2018
Bitcoin, Altcoins  and Trading Robots jan2018Bitcoin, Altcoins  and Trading Robots jan2018
Bitcoin, Altcoins and Trading Robots jan2018
 
Bitcoin and Blockchain overview
Bitcoin and Blockchain overviewBitcoin and Blockchain overview
Bitcoin and Blockchain overview
 
Bitcoin: Busienss and Technology Robot Overview
Bitcoin: Busienss and Technology Robot OverviewBitcoin: Busienss and Technology Robot Overview
Bitcoin: Busienss and Technology Robot Overview
 
ICOs Good The Bad and the Ugly
ICOs Good The Bad and the UglyICOs Good The Bad and the Ugly
ICOs Good The Bad and the Ugly
 
Tutorial on BlockChain and ICO in Commodity Trading
Tutorial on BlockChain and ICO in Commodity TradingTutorial on BlockChain and ICO in Commodity Trading
Tutorial on BlockChain and ICO in Commodity Trading
 
Introduction to Blockchain and BitCoin New Business Opportunties
Introduction to Blockchain and BitCoin New Business OpportuntiesIntroduction to Blockchain and BitCoin New Business Opportunties
Introduction to Blockchain and BitCoin New Business Opportunties
 
Rapid Economic Justifcation for Machine Learning in IoT
Rapid Economic Justifcation for Machine Learning in IoTRapid Economic Justifcation for Machine Learning in IoT
Rapid Economic Justifcation for Machine Learning in IoT
 
ROI of Machine Learning In IoT
ROI of Machine Learning In IoTROI of Machine Learning In IoT
ROI of Machine Learning In IoT
 

Recently uploaded

Cree_Rey_BrandIdentityKit.PDF_PersonalBd
Cree_Rey_BrandIdentityKit.PDF_PersonalBdCree_Rey_BrandIdentityKit.PDF_PersonalBd
Cree_Rey_BrandIdentityKit.PDF_PersonalBd
creerey
 
LA HUG - Video Testimonials with Chynna Morgan - June 2024
LA HUG - Video Testimonials with Chynna Morgan - June 2024LA HUG - Video Testimonials with Chynna Morgan - June 2024
LA HUG - Video Testimonials with Chynna Morgan - June 2024
Lital Barkan
 
Discover the innovative and creative projects that highlight my journey throu...
Discover the innovative and creative projects that highlight my journey throu...Discover the innovative and creative projects that highlight my journey throu...
Discover the innovative and creative projects that highlight my journey throu...
dylandmeas
 
Meas_Dylan_DMBS_PB1_2024-05XX_Revised.pdf
Meas_Dylan_DMBS_PB1_2024-05XX_Revised.pdfMeas_Dylan_DMBS_PB1_2024-05XX_Revised.pdf
Meas_Dylan_DMBS_PB1_2024-05XX_Revised.pdf
dylandmeas
 
Digital Transformation and IT Strategy Toolkit and Templates
Digital Transformation and IT Strategy Toolkit and TemplatesDigital Transformation and IT Strategy Toolkit and Templates
Digital Transformation and IT Strategy Toolkit and Templates
Aurelien Domont, MBA
 
ikea_woodgreen_petscharity_dog-alogue_digital.pdf
ikea_woodgreen_petscharity_dog-alogue_digital.pdfikea_woodgreen_petscharity_dog-alogue_digital.pdf
ikea_woodgreen_petscharity_dog-alogue_digital.pdf
agatadrynko
 
amptalk_RecruitingDeck_english_2024.06.05
amptalk_RecruitingDeck_english_2024.06.05amptalk_RecruitingDeck_english_2024.06.05
amptalk_RecruitingDeck_english_2024.06.05
marketing317746
 
Sustainability: Balancing the Environment, Equity & Economy
Sustainability: Balancing the Environment, Equity & EconomySustainability: Balancing the Environment, Equity & Economy
Sustainability: Balancing the Environment, Equity & Economy
Operational Excellence Consulting
 
Kseniya Leshchenko: Shared development support service model as the way to ma...
Kseniya Leshchenko: Shared development support service model as the way to ma...Kseniya Leshchenko: Shared development support service model as the way to ma...
Kseniya Leshchenko: Shared development support service model as the way to ma...
Lviv Startup Club
 
Project File Report BBA 6th semester.pdf
Project File Report BBA 6th semester.pdfProject File Report BBA 6th semester.pdf
Project File Report BBA 6th semester.pdf
RajPriye
 
BeMetals Presentation_May_22_2024 .pdf
BeMetals Presentation_May_22_2024   .pdfBeMetals Presentation_May_22_2024   .pdf
BeMetals Presentation_May_22_2024 .pdf
DerekIwanaka1
 
The effects of customers service quality and online reviews on customer loyal...
The effects of customers service quality and online reviews on customer loyal...The effects of customers service quality and online reviews on customer loyal...
The effects of customers service quality and online reviews on customer loyal...
balatucanapplelovely
 
Enterprise Excellence is Inclusive Excellence.pdf
Enterprise Excellence is Inclusive Excellence.pdfEnterprise Excellence is Inclusive Excellence.pdf
Enterprise Excellence is Inclusive Excellence.pdf
KaiNexus
 
Tata Group Dials Taiwan for Its Chipmaking Ambition in Gujarat’s Dholera
Tata Group Dials Taiwan for Its Chipmaking Ambition in Gujarat’s DholeraTata Group Dials Taiwan for Its Chipmaking Ambition in Gujarat’s Dholera
Tata Group Dials Taiwan for Its Chipmaking Ambition in Gujarat’s Dholera
Avirahi City Dholera
 
Cracking the Workplace Discipline Code Main.pptx
Cracking the Workplace Discipline Code Main.pptxCracking the Workplace Discipline Code Main.pptx
Cracking the Workplace Discipline Code Main.pptx
Workforce Group
 
Exploring Patterns of Connection with Social Dreaming
Exploring Patterns of Connection with Social DreamingExploring Patterns of Connection with Social Dreaming
Exploring Patterns of Connection with Social Dreaming
Nicola Wreford-Howard
 
ikea_woodgreen_petscharity_cat-alogue_digital.pdf
ikea_woodgreen_petscharity_cat-alogue_digital.pdfikea_woodgreen_petscharity_cat-alogue_digital.pdf
ikea_woodgreen_petscharity_cat-alogue_digital.pdf
agatadrynko
 
Buy Verified PayPal Account | Buy Google 5 Star Reviews
Buy Verified PayPal Account | Buy Google 5 Star ReviewsBuy Verified PayPal Account | Buy Google 5 Star Reviews
Buy Verified PayPal Account | Buy Google 5 Star Reviews
usawebmarket
 
RMD24 | Debunking the non-endemic revenue myth Marvin Vacquier Droop | First ...
RMD24 | Debunking the non-endemic revenue myth Marvin Vacquier Droop | First ...RMD24 | Debunking the non-endemic revenue myth Marvin Vacquier Droop | First ...
RMD24 | Debunking the non-endemic revenue myth Marvin Vacquier Droop | First ...
BBPMedia1
 
What are the main advantages of using HR recruiter services.pdf
What are the main advantages of using HR recruiter services.pdfWhat are the main advantages of using HR recruiter services.pdf
What are the main advantages of using HR recruiter services.pdf
HumanResourceDimensi1
 

Recently uploaded (20)

Cree_Rey_BrandIdentityKit.PDF_PersonalBd
Cree_Rey_BrandIdentityKit.PDF_PersonalBdCree_Rey_BrandIdentityKit.PDF_PersonalBd
Cree_Rey_BrandIdentityKit.PDF_PersonalBd
 
LA HUG - Video Testimonials with Chynna Morgan - June 2024
LA HUG - Video Testimonials with Chynna Morgan - June 2024LA HUG - Video Testimonials with Chynna Morgan - June 2024
LA HUG - Video Testimonials with Chynna Morgan - June 2024
 
Discover the innovative and creative projects that highlight my journey throu...
Discover the innovative and creative projects that highlight my journey throu...Discover the innovative and creative projects that highlight my journey throu...
Discover the innovative and creative projects that highlight my journey throu...
 
Meas_Dylan_DMBS_PB1_2024-05XX_Revised.pdf
Meas_Dylan_DMBS_PB1_2024-05XX_Revised.pdfMeas_Dylan_DMBS_PB1_2024-05XX_Revised.pdf
Meas_Dylan_DMBS_PB1_2024-05XX_Revised.pdf
 
Digital Transformation and IT Strategy Toolkit and Templates
Digital Transformation and IT Strategy Toolkit and TemplatesDigital Transformation and IT Strategy Toolkit and Templates
Digital Transformation and IT Strategy Toolkit and Templates
 
ikea_woodgreen_petscharity_dog-alogue_digital.pdf
ikea_woodgreen_petscharity_dog-alogue_digital.pdfikea_woodgreen_petscharity_dog-alogue_digital.pdf
ikea_woodgreen_petscharity_dog-alogue_digital.pdf
 
amptalk_RecruitingDeck_english_2024.06.05
amptalk_RecruitingDeck_english_2024.06.05amptalk_RecruitingDeck_english_2024.06.05
amptalk_RecruitingDeck_english_2024.06.05
 
Sustainability: Balancing the Environment, Equity & Economy
Sustainability: Balancing the Environment, Equity & EconomySustainability: Balancing the Environment, Equity & Economy
Sustainability: Balancing the Environment, Equity & Economy
 
Kseniya Leshchenko: Shared development support service model as the way to ma...
Kseniya Leshchenko: Shared development support service model as the way to ma...Kseniya Leshchenko: Shared development support service model as the way to ma...
Kseniya Leshchenko: Shared development support service model as the way to ma...
 
Project File Report BBA 6th semester.pdf
Project File Report BBA 6th semester.pdfProject File Report BBA 6th semester.pdf
Project File Report BBA 6th semester.pdf
 
BeMetals Presentation_May_22_2024 .pdf
BeMetals Presentation_May_22_2024   .pdfBeMetals Presentation_May_22_2024   .pdf
BeMetals Presentation_May_22_2024 .pdf
 
The effects of customers service quality and online reviews on customer loyal...
The effects of customers service quality and online reviews on customer loyal...The effects of customers service quality and online reviews on customer loyal...
The effects of customers service quality and online reviews on customer loyal...
 
Enterprise Excellence is Inclusive Excellence.pdf
Enterprise Excellence is Inclusive Excellence.pdfEnterprise Excellence is Inclusive Excellence.pdf
Enterprise Excellence is Inclusive Excellence.pdf
 
Tata Group Dials Taiwan for Its Chipmaking Ambition in Gujarat’s Dholera
Tata Group Dials Taiwan for Its Chipmaking Ambition in Gujarat’s DholeraTata Group Dials Taiwan for Its Chipmaking Ambition in Gujarat’s Dholera
Tata Group Dials Taiwan for Its Chipmaking Ambition in Gujarat’s Dholera
 
Cracking the Workplace Discipline Code Main.pptx
Cracking the Workplace Discipline Code Main.pptxCracking the Workplace Discipline Code Main.pptx
Cracking the Workplace Discipline Code Main.pptx
 
Exploring Patterns of Connection with Social Dreaming
Exploring Patterns of Connection with Social DreamingExploring Patterns of Connection with Social Dreaming
Exploring Patterns of Connection with Social Dreaming
 
ikea_woodgreen_petscharity_cat-alogue_digital.pdf
ikea_woodgreen_petscharity_cat-alogue_digital.pdfikea_woodgreen_petscharity_cat-alogue_digital.pdf
ikea_woodgreen_petscharity_cat-alogue_digital.pdf
 
Buy Verified PayPal Account | Buy Google 5 Star Reviews
Buy Verified PayPal Account | Buy Google 5 Star ReviewsBuy Verified PayPal Account | Buy Google 5 Star Reviews
Buy Verified PayPal Account | Buy Google 5 Star Reviews
 
RMD24 | Debunking the non-endemic revenue myth Marvin Vacquier Droop | First ...
RMD24 | Debunking the non-endemic revenue myth Marvin Vacquier Droop | First ...RMD24 | Debunking the non-endemic revenue myth Marvin Vacquier Droop | First ...
RMD24 | Debunking the non-endemic revenue myth Marvin Vacquier Droop | First ...
 
What are the main advantages of using HR recruiter services.pdf
What are the main advantages of using HR recruiter services.pdfWhat are the main advantages of using HR recruiter services.pdf
What are the main advantages of using HR recruiter services.pdf
 

AI Class Topic 6: Easy Way to Learn Deep Learning AI Technologies

  • 1. WELCOME TO: Deep Learning AI Technologies 1. Neural Networks 2. CNN By Adj Prof. Giuseppe Mascarella giuseppe@valueamplify.com
  • 3. Stochastic Gradient Descent for Bayesian Neural Networks DEFINITIONS A) BAYESIAN Bayesian inference is a method of statistical inference in which Bayes' theorem is used to update the probability for a hypothesis as more evidence or information becomes available. B) Heuristic Experimenting, evaluating possible answers or solutions, or by trial and error Shortcuts to make decisions based on past events or traits that are representative of or similar to the current situation.
  • 5. What Is a Neural Network” A is a set of interconnected layers. The inputs are the first layer, and are connected to an output layer by an acyclic graph comprised of weighted edges and nodes. A NN is a DNN (Deep Neural Networks) when you have many hidden layers has more accuracy. All nodes in a layer are connected by the weighted edges to nodes in the next layer. To compute the output of the network for a particular input, the value is set by calculating the weighted sum of the values of the nodes from the previous layer. An activation function is then applied to that weighted sum.
  • 6. Neural Networks Basics X1 - Is the weather good? X2 - Does your boyfriend or girlfriend want to accompany you? X3 - Is the festival near public transit? (You don't own a car). The artificial neuron are called: perceptron • w1=6 for the weather • w2=2 • w3=2 for the other conditions. • Threshold (Bias Toward Cheese)= 3 Biz Problem To Solve: Predict, Will John Go To The Cheese Festival This Weekend? W=> Tool for a device that makes decisions by weighing up evidence and previous results. NAND Electrical Circuit Operator 0,1 Bias: how easy it is to get the perceptron to fire W 3
  • 7. Sigmoid Neuron • Learning algorithms which can automatically tune neurons: • Weights • biases 8 vs 9 = =
  • 8.
  • 9.
  • 10.
  • 11.
  • 12.
  • 13.
  • 14.
  • 15.
  • 16.
  • 17. Backpropagation! The algo that computes the best Gradient
  • 18.
  • 19.
  • 20.
  • 21. Cost Function: MSE (Mean Squared Error) n is the total number of training inputs, a is the vector of outputs from the network w/x as input Sum is over all training inputs, x Y=(m n +x) C = w2-w1/(y2-y1)
  • 22.
  • 24.
  • 25.
  • 26.
  • 27. How To Configure a NN (Part 1) https://docs.microsoft.com/en-us/azure/machine-learning/studio-module-reference/two-class-neural-network 1. Category 2. Parameters (Hyperparameters) 3. Hidden Layers 4. Hidden Nodes, default in a hidden layer is 100 nodes. 5. Learning rate, define the size of the step taken at each iteration, before correction. (i.e. a larger value for learning rate can cause the model to converge faster, but it can overshoot local minima.) 6. Number of learning iterations, specify the maximum number of times the algorithm should process the training cases. 7. Initial Learning Weights Diameter, specify the node weights at the start of the learning process. 8. Momentum, specify a weight to apply during learning to nodes from previous iterations. https://distill.pub/2017/momentum/ Scripted, custom CNN input Picture [28, 28]; hidden C1 [5, 12, 12] from Picture convolve { InputShape = [28, 28]; KernelShape = [ 5, 5]; Stride = [ 2, 2]; MapCount = 5; }
  • 28.
  • 29. How To Configure a NN (Part 2) • Type of normalizer, select a method to use for feature normalization. The following normalization methods are supported: • Binning normalizer: The binning normalizer creates bins of equal size, and then normalizes every value in each bin, dividing by the total number of bins. • Gaussian normalizer: The Gaussian normalizer rescales the values of each feature to have mean 0 and variance 1. This is done by computing the mean and the variance of each feature. For each instance, the mean value is subtracted, and the result divided by the square root of the variance (the standard deviation). • Min-max normalizer: The min-max normalizer linearly rescales every feature to the [0,1] interval.Rescaling to the [0,1] interval is done by shifting the values of each feature so that the minimal value is 0, and then dividing by the new maximal value (which is the difference between the original maximal and minimal values). • Do not normalize: No normalization is performed. • Shuffle examples option to shuffle cases between iterations. If you deselect this option, cases are processed in exactly the same order each time you run the experiment. • Random number seed, type a value to use as the seed. Specifying a seed value is useful when you want to ensure repeatability across runs of the same experiment. Otherwise, a system clock value is used as the seed, which can cause slightly different results each time you run the experiment. • Allow unknown categorical levels option to create a grouping for unknown values in the training and validation sets. The model might be less precise on known values but provide better predictions for new (unknown) values. If you deselect this option, the model can accept only the values contained in the training data.
  • 31. Tune Model Hyperparameters • Integrated train and tune: You configure a set of parameters to use, and then let the module iterate over multiple combinations, measuring accuracy until it finds a "best" model. With most learner modules, you can choose which parameters should be changed during the training process, and which should remain fixed. •Depending on how long you want the tuning process to run, you might decide to exhaustively test all combinations, or you could shorten the process by establishing a grid of parameter combinations and testing a randomized subset of the parameter grid. • Cross validation with tuning: With this option, you divide your data into some number of folds and then build and test models on each fold. This method provides the best accuracy and can help find problems with the dataset; however, it takes longer to train.
  • 32. Assignment: NN ML Experiment Reverse Engineering • https://gallery.azure.ai/Experiment/pranab-p181a35-nlp-final-exam
  • 33. WELCOME TO: Deep Learning AI Technologies 1. Neural Networks 2. CNN(Convoluted Networks) By Adj Prof. Giuseppe Mascarella giuseppe@valueamplify.com
  • 34. CNN Definitions A. Inspired by biological processes[7][8][9][10] in that the connectivity pattern between neurons resembles the organization of the animal visual cortex. Individual cortical neurons respond to stimuli only in a restricted region of the visual field known as the receptive field. The receptive fields of different neurons partially overlap such that they cover the entire visual field. B. The name “convolutional neural network” indicates that the network employs a mathematical operation called convolution that is a mathematical operation on two functions (f and g) that produces a third function (f*g) expressing how the shape of one is modified by the other. C. The convolutional layer is the core building block of a CNN. The layer's parameters consist of a set of learnable filters (or kernels), which have a small receptive field, but extend through the full depth of the input volume. D. They are also known as shift invariant or space invariant artificial neural networks (SIANN), based on their shared-weights architecture and translation invariance characteristics.
  • 35. CNN Applications: image and video recognition, recommender systems, image classification, medical image analysis, natural language processing, and financial time series. WHY? CNNs use relatively little pre-processing compared to other image classification algorithms. This means that the network learns the filters that in traditional algorithms were hand-engineered. This independence from prior knowledge and human effort in feature design is a major advantage.
  • 36. What Problem Is CNN Trying To Solve? Adaptation for education purpose from: https://www.youtube.com/watch?v=2-Ol7ZB0MmU
  • 37. CNN Deep Learning Is a Brilliant A Series Of Classifiers Orchestrated in Layers
  • 39. Derivative work from: A friendly introduction to Convolutional Neural Networks and Image Recognition by Serrano
  • 40.
  • 41.
  • 42.
  • 43.
  • 44.
  • 45.
  • 46.
  • 47.
  • 51.
  • 52.
  • 54.
  • 55.
  • 56.
  • 57.
  • 58. Create Random Numbers And Gradient Descend
  • 59. CNN
  • 60. LSTM (Long short-term memory) Algo Long short-term memory (LSTM) is an artificial recurrent neural network (RNN) architecture used in the field of deep learning. Unlike standard feedforward neural networks, LSTM has feedback connections.
  • 61. • The aim of predictive maintenance (PdM) is first to predict when equipment failure might occur, and secondly, to prevent the occurrence of the failure by performing maintenance. ... When predictive maintenance is working effectively as a maintenance strategy, maintenance is only performed on machines when it is required. • The asset of interest has a progressing degradation pattern, which is reflected in the asset's sensor measurements." Some FMEA shows that assets fail without a detectable degradation pattern. Also, sensor (performance) data is only one piece of the picture. Asset configuration will impact RUL also. If I swap an old fan blade (or a non-OEM fan blade, etc.) into my engine, it will alter RUL. If the model doesn't know how many cycles the fan blade has on it, it will break.