SlideShare ist ein Scribd-Unternehmen logo
1 von 41
Lesson 6
Deep Learning
Legal Notices and Disclaimers
This presentation is for informational purposes only. INTEL MAKES NO
WARRANTIES, EXPRESS OR IMPLIED, IN THIS SUMMARY.
Intel technologies’ features and benefits depend on system configuration and may
require enabled hardware, software or service activation. Performance varies
depending on system configuration. Check with your system manufacturer or retailer
or learn more at intel.com.
This sample source code is released under the Intel Sample Source Code License
Agreement.
Intel and the Intel logo are trademarks of Intel Corporation in the U.S. and/or other
countries.
*Other names and brands may be claimed as the property of others.
Copyright Š 2018, Intel Corporation. All rights reserved.
3
Learning Objectives
• Identify the types of problems Deep Learning resolves
• Describe the steps in building a neural network model
• Describe a convolutional neural network
• Explain transfer learning and why it’s useful
• Identify common Deep Learning architectures
You will be able to:
5
Deep Learning
“Machine learning that involves using
very complicated models called “deep
neural networks”." (Intel)
Models determine best representation
of original data; in classic machine
learning, humans must do this.
6
Classic
Machine
Learning
Step 1: Determine
features.
Step 2: Feed them
through model.
“Arjun"
Neural Network
“Arjun"
Deep
Learning
Steps 1 and 2
are combined
into 1 step.
Deep Learning Differences
Machine
Learning
Classifier
Algorithm
Feature
Detection
7
Deep Learning Problem Types
Deep Learning can solve multiple supervised and unsupervised problems.
• The majority of its success has been when working
with images, natural language, and audio data.
• Image classification and detection.
• Semantic segmentation.
• Natural language object retrieval.
• Speech recognition and language translation.
8
Classification and Detection
Detect and label the image
• Person
• Motor Bike
https://people.eecs.berkeley.edu/~jhoffman/talks/lsda-baylearn2014.pdf
9
Semantic Segmentation
Label every pixel
https://people.eecs.berkeley.edu/~jhoffman/talks/lsda-baylearn2014.pdf
10
Natural Language Object Retrieval
http://arxiv.org/pdf/1511.04164v3.pdf
11
Speech Recognition and Language Translation
http://svail.github.io/mandarin/
The same architecture can be used for speech recognition in English, or
in Mandarin Chinese.
Formulating Supervised Learning Tools
13
For a supervised learning problem:
• Collect a labeled dataset (features and target labels).
• Choose the model.
• Choose an evaluation metric:
“What to use to measure performance.”
• Choose an optimization method:1
“How to find the model configuration that gives the best performance.”
1 There are standard methods to use for different models and metrics.
Which Model?
14
There are many models that represent the problem and make decisions in different
ways, each with their own advantages and disadvantages.
• DL models are biologically inspired.
• The main building block is a neuron.
Neuron
Neuron
15
A neuron multiplies each feature by a weight and then adds these
values together.
• Z = X1W1+ X2W2+ X3W3
Z
X1
X2
X3
W2
W1
W3
Neuron
16
This value is then put through a function called the activation function.
• There are several activation functions
that can be used.
• The output of the neuron is the output
of the activation function.
Activation
Function
X1
X2
X3
W2
W1
W3
Output
Perceptron
17
A neuron with a simple activation function can solve linearly
separable problems.
• These are problems where the different
classes can be separated by a line.
• The Perceptron: one of the earliest neural
network models that used neurons with
simple activation functions.
Perceptron
18
Problems where the labels cannot be separated by a single line are not
solvable by a single neuron.
• This is a major limitation, and one of the
reasons for the first AI winter, that was
discussed in lesson 1.
19
Fully Connected Network
http://svail.github.io/mandarin/
More complicated problems can be solved by connecting multiple
neurons together and using more complicated activation functions.
• Organized into layers of neurons.
• Each neuron is connected to every
neuron in the previous layer.
• Each layer transforms the output of
the previous layer and then passes it
on to the next.
• Every connection has a separate weight.
Deep Learning
Deep Learning refers to when many layers are used to build deep networks.
• State-of-the-art models use hundreds of layers.
• Deep layers tend to decrease in width.
• Successive layers transform inputs with two effects:
• Compression: each layer is asked to summarize the
input in a way that best serves the task.
• Extraction: the model succeeds when each layer
extracts task-relevant information.
Input
Output
21
Steps in Building a Fully Connected Network
To build a fully connected network a user needs to:
• Define the network architecture.
• How many layers and neurons?
• Define what activation function to
use for each neuron.
• Define an evaluation metric.
• The values for the weights are learned
during model training.
http://svail.github.io/mandarin/
22
Evaluation Metric
The metric used will depend on the problem being solved.
Some examples include:
• Regression
• Mean Squared Error
• Classification
• Categorical Cross-Entropy
• Multi-Label classification
• Binary Cross-Entropy
23
Fully Connected Network Problems
Not optimal for detecting features.
• Computationally intensive – heavy memory usage.
25
Convolutional Neural Network
Convolutional neural networks reduce the required
computation and are good for detecting features.
• Each neuron is connected to a small set of nearby
neurons in the previous layer.
• The same set of weights are used for each neuron.
• Ideal for spatial feature recognition.
• Example: image recognition
• Cheaper on resources due to fewer connections.
http://svail.github.io/mandarin/
26
Convolutions as Feature Detectors
-1 1 -1
-1 1 -1
-1 1 -1
Vertical Line Detector
-1 -1 -1
1 1 1
-1 -1 -1
Horizontal Line Detector
-1 -1 -1
-1 1 1
-1 1 1
Corner Detector
Convolutions can be thought of as “local feature detectors”.
27
Convolutions
28
Convolutional Neural Network
Convolutions
Fully Connected
30
Transfer Learning
There are difficulties with building convolutional neural networks.
• They require huge datasets.
• There is a large amount of required computation.
• A large amount of time is spent experimenting to
get the hyper-parameters correct.
• It would be very difficult to train a famous,
competition-winning model from scratch
31
Transfer Learning
We can take advantage of existing DL models.
• Early layers in a neural network are the hardest (slowest) to train.
• These ”primitive” features should be general across many image
classification tasks.
• Later layers in the network capture features that are more particular to
the specific image classification problem.
• Later layers are easier (quicker) to train since adjusting their weights has
a more immediate impact on the final result.
32
Transfer Learning
Keeping the early layers of a pre-trained network, and re-training the
later layers for a specific application, is called transfer learning.
• Results of the training are weights (numbers) that are easy to store.
• Using pre-trained layers reduces the amount of required data.
33
Convolutional Neural Network
Convolutions
Fully Connected
Fix Weights
Train only the
last layer
34
Transfer Learning Options
The additional training of a pre-trained network on a specific new
dataset is referred to as “fine-tuning”.
• Choose “how much” and “how far back” to fine-tune.
• Should I train just the very last layer, or go back a few layers?
• Re-train the entire network (from the starting-point of the existing
network)?
36
AlexNet
37
VGG 16
38
Inception
39
MobileNets
Efficient models for mobile and embedded vision applications.
MobileNet models can be applied to various recognition tasks for efficient device intelligence.
40
Learning Objectives
• Identify the types of problems Deep Learning resolves.
• Describe the steps in building a neural network model.
• Describe a convolutional neural network.
• Explain transfer learning and why it’s useful.
• Identify common Deep Learning architectures.
In this session we worked to:
Deep learning summary

Weitere ähnliche Inhalte

Was ist angesagt?

Computer Vision for Beginners
Computer Vision for BeginnersComputer Vision for Beginners
Computer Vision for Beginners
Sanghamitra Deb
 
2017 (albawi-alkabi)image-net classification with deep convolutional neural n...
2017 (albawi-alkabi)image-net classification with deep convolutional neural n...2017 (albawi-alkabi)image-net classification with deep convolutional neural n...
2017 (albawi-alkabi)image-net classification with deep convolutional neural n...
ali hassan
 
NEURAL Network Design Training
NEURAL Network Design  TrainingNEURAL Network Design  Training
NEURAL Network Design Training
ESCOM
 
Learn to Build an App to Find Similar Images using Deep Learning- Piotr Teterwak
Learn to Build an App to Find Similar Images using Deep Learning- Piotr TeterwakLearn to Build an App to Find Similar Images using Deep Learning- Piotr Teterwak
Learn to Build an App to Find Similar Images using Deep Learning- Piotr Teterwak
PyData
 

Was ist angesagt? (20)

Foundations: Artificial Neural Networks
Foundations: Artificial Neural NetworksFoundations: Artificial Neural Networks
Foundations: Artificial Neural Networks
 
"An Introduction to Machine Learning and How to Teach Machines to See," a Pre...
"An Introduction to Machine Learning and How to Teach Machines to See," a Pre..."An Introduction to Machine Learning and How to Teach Machines to See," a Pre...
"An Introduction to Machine Learning and How to Teach Machines to See," a Pre...
 
Computer Vision for Beginners
Computer Vision for BeginnersComputer Vision for Beginners
Computer Vision for Beginners
 
2017 (albawi-alkabi)image-net classification with deep convolutional neural n...
2017 (albawi-alkabi)image-net classification with deep convolutional neural n...2017 (albawi-alkabi)image-net classification with deep convolutional neural n...
2017 (albawi-alkabi)image-net classification with deep convolutional neural n...
 
NEURAL Network Design Training
NEURAL Network Design  TrainingNEURAL Network Design  Training
NEURAL Network Design Training
 
Machine Learning Overview
Machine Learning OverviewMachine Learning Overview
Machine Learning Overview
 
Learn to Build an App to Find Similar Images using Deep Learning- Piotr Teterwak
Learn to Build an App to Find Similar Images using Deep Learning- Piotr TeterwakLearn to Build an App to Find Similar Images using Deep Learning- Piotr Teterwak
Learn to Build an App to Find Similar Images using Deep Learning- Piotr Teterwak
 
A survey on the layers of convolutional Neural Network
A survey on the layers of convolutional Neural NetworkA survey on the layers of convolutional Neural Network
A survey on the layers of convolutional Neural Network
 
Ml9 introduction to-unsupervised_learning_and_clustering_methods
Ml9 introduction to-unsupervised_learning_and_clustering_methodsMl9 introduction to-unsupervised_learning_and_clustering_methods
Ml9 introduction to-unsupervised_learning_and_clustering_methods
 
Deep learning crash course
Deep learning crash courseDeep learning crash course
Deep learning crash course
 
Introduction to-machine-learning
Introduction to-machine-learningIntroduction to-machine-learning
Introduction to-machine-learning
 
Neural Networks and Deep Learning Basics
Neural Networks and Deep Learning BasicsNeural Networks and Deep Learning Basics
Neural Networks and Deep Learning Basics
 
Deep Learning Sample Class (Jon Lederman)
Deep Learning Sample Class (Jon Lederman)Deep Learning Sample Class (Jon Lederman)
Deep Learning Sample Class (Jon Lederman)
 
Machine learning and_neural_network_lecture_slide_ece_dku
Machine learning and_neural_network_lecture_slide_ece_dkuMachine learning and_neural_network_lecture_slide_ece_dku
Machine learning and_neural_network_lecture_slide_ece_dku
 
Lesson 33
Lesson 33Lesson 33
Lesson 33
 
Hand Written Digit Classification
Hand Written Digit ClassificationHand Written Digit Classification
Hand Written Digit Classification
 
Neural networks
Neural networksNeural networks
Neural networks
 
Face Recognition: From Scratch To Hatch
Face Recognition: From Scratch To HatchFace Recognition: From Scratch To Hatch
Face Recognition: From Scratch To Hatch
 
Regularization in deep learning
Regularization in deep learningRegularization in deep learning
Regularization in deep learning
 
Deep learning Introduction and Basics
Deep learning  Introduction and BasicsDeep learning  Introduction and Basics
Deep learning Introduction and Basics
 

Ähnlich wie Deep learning summary

Table of Contents
Table of ContentsTable of Contents
Table of Contents
butest
 
Network recasting
Network recastingNetwork recasting
Network recasting
NAVER Engineering
 
Unit one ppt of deeep learning which includes Ann cnn
Unit one ppt of  deeep learning which includes Ann cnnUnit one ppt of  deeep learning which includes Ann cnn
Unit one ppt of deeep learning which includes Ann cnn
kartikaursang53
 
NVIDIA 深度學習教育機構 (DLI): Medical image segmentation using digits
NVIDIA 深度學習教育機構 (DLI): Medical image segmentation using digitsNVIDIA 深度學習教育機構 (DLI): Medical image segmentation using digits
NVIDIA 深度學習教育機構 (DLI): Medical image segmentation using digits
NVIDIA Taiwan
 
nil-100128213838-phpapp02.pptx
nil-100128213838-phpapp02.pptxnil-100128213838-phpapp02.pptx
nil-100128213838-phpapp02.pptx
dlakmlkfma
 
Deep learning - a primer
Deep learning - a primerDeep learning - a primer
Deep learning - a primer
Uwe Friedrichsen
 
Deep learning - a primer
Deep learning - a primerDeep learning - a primer
Deep learning - a primer
Shirin Elsinghorst
 

Ähnlich wie Deep learning summary (20)

Deep learning with keras
Deep learning with kerasDeep learning with keras
Deep learning with keras
 
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
 
Table of Contents
Table of ContentsTable of Contents
Table of Contents
 
Computer Design Concepts for Machine Learning
Computer Design Concepts for Machine LearningComputer Design Concepts for Machine Learning
Computer Design Concepts for Machine Learning
 
Distilling dark knowledge from neural networks
Distilling dark knowledge from neural networksDistilling dark knowledge from neural networks
Distilling dark knowledge from neural networks
 
Activation functions and Training Algorithms for Deep Neural network
Activation functions and Training Algorithms for Deep Neural networkActivation functions and Training Algorithms for Deep Neural network
Activation functions and Training Algorithms for Deep Neural network
 
nil-100128213838-phpapp02.pdf
nil-100128213838-phpapp02.pdfnil-100128213838-phpapp02.pdf
nil-100128213838-phpapp02.pdf
 
Network recasting
Network recastingNetwork recasting
Network recasting
 
Unit one ppt of deeep learning which includes Ann cnn
Unit one ppt of  deeep learning which includes Ann cnnUnit one ppt of  deeep learning which includes Ann cnn
Unit one ppt of deeep learning which includes Ann cnn
 
11_Saloni Malhotra_SummerTraining_PPT.pptx
11_Saloni Malhotra_SummerTraining_PPT.pptx11_Saloni Malhotra_SummerTraining_PPT.pptx
11_Saloni Malhotra_SummerTraining_PPT.pptx
 
NVIDIA 深度學習教育機構 (DLI): Medical image segmentation using digits
NVIDIA 深度學習教育機構 (DLI): Medical image segmentation using digitsNVIDIA 深度學習教育機構 (DLI): Medical image segmentation using digits
NVIDIA 深度學習教育機構 (DLI): Medical image segmentation using digits
 
nil-100128213838-phpapp02.pptx
nil-100128213838-phpapp02.pptxnil-100128213838-phpapp02.pptx
nil-100128213838-phpapp02.pptx
 
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”
 
cnn ppt.pptx
cnn ppt.pptxcnn ppt.pptx
cnn ppt.pptx
 
Teach a neural network to read handwriting
Teach a neural network to read handwritingTeach a neural network to read handwriting
Teach a neural network to read handwriting
 
Deep learning - a primer
Deep learning - a primerDeep learning - a primer
Deep learning - a primer
 
Deep learning - a primer
Deep learning - a primerDeep learning - a primer
Deep learning - a primer
 
Introduction to deep learning
Introduction to deep learningIntroduction to deep learning
Introduction to deep learning
 
EssentialsOfMachineLearning.pdf
EssentialsOfMachineLearning.pdfEssentialsOfMachineLearning.pdf
EssentialsOfMachineLearning.pdf
 
Entity embeddings for categorical data
Entity embeddings for categorical dataEntity embeddings for categorical data
Entity embeddings for categorical data
 

Mehr von ankit_ppt

Mehr von ankit_ppt (20)

07 learning
07 learning07 learning
07 learning
 
06 image features
06 image features06 image features
06 image features
 
05 contours seg_matching
05 contours seg_matching05 contours seg_matching
05 contours seg_matching
 
04 image transformations_ii
04 image transformations_ii04 image transformations_ii
04 image transformations_ii
 
03 image transformations_i
03 image transformations_i03 image transformations_i
03 image transformations_i
 
02 image processing
02 image processing02 image processing
02 image processing
 
01 foundations
01 foundations01 foundations
01 foundations
 
Word2 vec
Word2 vecWord2 vec
Word2 vec
 
Text similarity measures
Text similarity measuresText similarity measures
Text similarity measures
 
Text generation and_advanced_topics
Text generation and_advanced_topicsText generation and_advanced_topics
Text generation and_advanced_topics
 
Nlp toolkits and_preprocessing_techniques
Nlp toolkits and_preprocessing_techniquesNlp toolkits and_preprocessing_techniques
Nlp toolkits and_preprocessing_techniques
 
Matrix decomposition and_applications_to_nlp
Matrix decomposition and_applications_to_nlpMatrix decomposition and_applications_to_nlp
Matrix decomposition and_applications_to_nlp
 
Machine learning and_nlp
Machine learning and_nlpMachine learning and_nlp
Machine learning and_nlp
 
Latent dirichlet allocation_and_topic_modeling
Latent dirichlet allocation_and_topic_modelingLatent dirichlet allocation_and_topic_modeling
Latent dirichlet allocation_and_topic_modeling
 
Intro to nlp
Intro to nlpIntro to nlp
Intro to nlp
 
Ot regularization and_gradient_descent
Ot regularization and_gradient_descentOt regularization and_gradient_descent
Ot regularization and_gradient_descent
 
Ml8 boosting and-stacking
Ml8 boosting and-stackingMl8 boosting and-stacking
Ml8 boosting and-stacking
 
Ml7 bagging
Ml7 baggingMl7 bagging
Ml7 bagging
 
Ml6 decision trees
Ml6 decision treesMl6 decision trees
Ml6 decision trees
 
Ml5 svm and-kernels
Ml5 svm and-kernelsMl5 svm and-kernels
Ml5 svm and-kernels
 

KĂźrzlich hochgeladen

Cara Menggugurkan Sperma Yang Masuk Rahim Biyar Tidak Hamil
Cara Menggugurkan Sperma Yang Masuk Rahim Biyar Tidak HamilCara Menggugurkan Sperma Yang Masuk Rahim Biyar Tidak Hamil
Cara Menggugurkan Sperma Yang Masuk Rahim Biyar Tidak Hamil
Cara Menggugurkan Kandungan 087776558899
 
Double rodded leveling 1 pdf activity 01
Double rodded leveling 1 pdf activity 01Double rodded leveling 1 pdf activity 01
Double rodded leveling 1 pdf activity 01
KreezheaRecto
 
XXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXX
XXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXX
XXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXX
ssuser89054b
 
AKTU Computer Networks notes --- Unit 3.pdf
AKTU Computer Networks notes ---  Unit 3.pdfAKTU Computer Networks notes ---  Unit 3.pdf
AKTU Computer Networks notes --- Unit 3.pdf
ankushspencer015
 
Call Girls in Ramesh Nagar Delhi 💯 Call Us 🔝9953056974 🔝 Escort Service
Call Girls in Ramesh Nagar Delhi 💯 Call Us 🔝9953056974 🔝 Escort ServiceCall Girls in Ramesh Nagar Delhi 💯 Call Us 🔝9953056974 🔝 Escort Service
Call Girls in Ramesh Nagar Delhi 💯 Call Us 🔝9953056974 🔝 Escort Service
9953056974 Low Rate Call Girls In Saket, Delhi NCR
 
Top Rated Call Girls In chittoor 📱 {7001035870} VIP Escorts chittoor
Top Rated Call Girls In chittoor 📱 {7001035870} VIP Escorts chittoorTop Rated Call Girls In chittoor 📱 {7001035870} VIP Escorts chittoor
Top Rated Call Girls In chittoor 📱 {7001035870} VIP Escorts chittoor
dharasingh5698
 
UNIT - IV - Air Compressors and its Performance
UNIT - IV - Air Compressors and its PerformanceUNIT - IV - Air Compressors and its Performance
UNIT - IV - Air Compressors and its Performance
sivaprakash250
 
Call Girls in Netaji Nagar, Delhi 💯 Call Us 🔝9953056974 🔝 Escort Service
Call Girls in Netaji Nagar, Delhi 💯 Call Us 🔝9953056974 🔝 Escort ServiceCall Girls in Netaji Nagar, Delhi 💯 Call Us 🔝9953056974 🔝 Escort Service
Call Girls in Netaji Nagar, Delhi 💯 Call Us 🔝9953056974 🔝 Escort Service
9953056974 Low Rate Call Girls In Saket, Delhi NCR
 

KĂźrzlich hochgeladen (20)

Water Industry Process Automation & Control Monthly - April 2024
Water Industry Process Automation & Control Monthly - April 2024Water Industry Process Automation & Control Monthly - April 2024
Water Industry Process Automation & Control Monthly - April 2024
 
Cara Menggugurkan Sperma Yang Masuk Rahim Biyar Tidak Hamil
Cara Menggugurkan Sperma Yang Masuk Rahim Biyar Tidak HamilCara Menggugurkan Sperma Yang Masuk Rahim Biyar Tidak Hamil
Cara Menggugurkan Sperma Yang Masuk Rahim Biyar Tidak Hamil
 
Double rodded leveling 1 pdf activity 01
Double rodded leveling 1 pdf activity 01Double rodded leveling 1 pdf activity 01
Double rodded leveling 1 pdf activity 01
 
Top Rated Pune Call Girls Budhwar Peth ⟟ 6297143586 ⟟ Call Me For Genuine Se...
Top Rated  Pune Call Girls Budhwar Peth ⟟ 6297143586 ⟟ Call Me For Genuine Se...Top Rated  Pune Call Girls Budhwar Peth ⟟ 6297143586 ⟟ Call Me For Genuine Se...
Top Rated Pune Call Girls Budhwar Peth ⟟ 6297143586 ⟟ Call Me For Genuine Se...
 
FEA Based Level 3 Assessment of Deformed Tanks with Fluid Induced Loads
FEA Based Level 3 Assessment of Deformed Tanks with Fluid Induced LoadsFEA Based Level 3 Assessment of Deformed Tanks with Fluid Induced Loads
FEA Based Level 3 Assessment of Deformed Tanks with Fluid Induced Loads
 
Work-Permit-Receiver-in-Saudi-Aramco.pptx
Work-Permit-Receiver-in-Saudi-Aramco.pptxWork-Permit-Receiver-in-Saudi-Aramco.pptx
Work-Permit-Receiver-in-Saudi-Aramco.pptx
 
Block diagram reduction techniques in control systems.ppt
Block diagram reduction techniques in control systems.pptBlock diagram reduction techniques in control systems.ppt
Block diagram reduction techniques in control systems.ppt
 
Booking open Available Pune Call Girls Pargaon 6297143586 Call Hot Indian Gi...
Booking open Available Pune Call Girls Pargaon  6297143586 Call Hot Indian Gi...Booking open Available Pune Call Girls Pargaon  6297143586 Call Hot Indian Gi...
Booking open Available Pune Call Girls Pargaon 6297143586 Call Hot Indian Gi...
 
Online banking management system project.pdf
Online banking management system project.pdfOnline banking management system project.pdf
Online banking management system project.pdf
 
XXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXX
XXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXX
XXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXX
 
AKTU Computer Networks notes --- Unit 3.pdf
AKTU Computer Networks notes ---  Unit 3.pdfAKTU Computer Networks notes ---  Unit 3.pdf
AKTU Computer Networks notes --- Unit 3.pdf
 
(INDIRA) Call Girl Meerut Call Now 8617697112 Meerut Escorts 24x7
(INDIRA) Call Girl Meerut Call Now 8617697112 Meerut Escorts 24x7(INDIRA) Call Girl Meerut Call Now 8617697112 Meerut Escorts 24x7
(INDIRA) Call Girl Meerut Call Now 8617697112 Meerut Escorts 24x7
 
Call Girls in Ramesh Nagar Delhi 💯 Call Us 🔝9953056974 🔝 Escort Service
Call Girls in Ramesh Nagar Delhi 💯 Call Us 🔝9953056974 🔝 Escort ServiceCall Girls in Ramesh Nagar Delhi 💯 Call Us 🔝9953056974 🔝 Escort Service
Call Girls in Ramesh Nagar Delhi 💯 Call Us 🔝9953056974 🔝 Escort Service
 
Call Girls Wakad Call Me 7737669865 Budget Friendly No Advance Booking
Call Girls Wakad Call Me 7737669865 Budget Friendly No Advance BookingCall Girls Wakad Call Me 7737669865 Budget Friendly No Advance Booking
Call Girls Wakad Call Me 7737669865 Budget Friendly No Advance Booking
 
Top Rated Call Girls In chittoor 📱 {7001035870} VIP Escorts chittoor
Top Rated Call Girls In chittoor 📱 {7001035870} VIP Escorts chittoorTop Rated Call Girls In chittoor 📱 {7001035870} VIP Escorts chittoor
Top Rated Call Girls In chittoor 📱 {7001035870} VIP Escorts chittoor
 
(INDIRA) Call Girl Aurangabad Call Now 8617697112 Aurangabad Escorts 24x7
(INDIRA) Call Girl Aurangabad Call Now 8617697112 Aurangabad Escorts 24x7(INDIRA) Call Girl Aurangabad Call Now 8617697112 Aurangabad Escorts 24x7
(INDIRA) Call Girl Aurangabad Call Now 8617697112 Aurangabad Escorts 24x7
 
UNIT - IV - Air Compressors and its Performance
UNIT - IV - Air Compressors and its PerformanceUNIT - IV - Air Compressors and its Performance
UNIT - IV - Air Compressors and its Performance
 
chapter 5.pptx: drainage and irrigation engineering
chapter 5.pptx: drainage and irrigation engineeringchapter 5.pptx: drainage and irrigation engineering
chapter 5.pptx: drainage and irrigation engineering
 
Call Girls in Netaji Nagar, Delhi 💯 Call Us 🔝9953056974 🔝 Escort Service
Call Girls in Netaji Nagar, Delhi 💯 Call Us 🔝9953056974 🔝 Escort ServiceCall Girls in Netaji Nagar, Delhi 💯 Call Us 🔝9953056974 🔝 Escort Service
Call Girls in Netaji Nagar, Delhi 💯 Call Us 🔝9953056974 🔝 Escort Service
 
Unit 1 - Soil Classification and Compaction.pdf
Unit 1 - Soil Classification and Compaction.pdfUnit 1 - Soil Classification and Compaction.pdf
Unit 1 - Soil Classification and Compaction.pdf
 

Deep learning summary

  • 2. Legal Notices and Disclaimers This presentation is for informational purposes only. INTEL MAKES NO WARRANTIES, EXPRESS OR IMPLIED, IN THIS SUMMARY. Intel technologies’ features and benefits depend on system configuration and may require enabled hardware, software or service activation. Performance varies depending on system configuration. Check with your system manufacturer or retailer or learn more at intel.com. This sample source code is released under the Intel Sample Source Code License Agreement. Intel and the Intel logo are trademarks of Intel Corporation in the U.S. and/or other countries. *Other names and brands may be claimed as the property of others. Copyright Š 2018, Intel Corporation. All rights reserved.
  • 3. 3 Learning Objectives • Identify the types of problems Deep Learning resolves • Describe the steps in building a neural network model • Describe a convolutional neural network • Explain transfer learning and why it’s useful • Identify common Deep Learning architectures You will be able to:
  • 4.
  • 5. 5 Deep Learning “Machine learning that involves using very complicated models called “deep neural networks”." (Intel) Models determine best representation of original data; in classic machine learning, humans must do this.
  • 6. 6 Classic Machine Learning Step 1: Determine features. Step 2: Feed them through model. “Arjun" Neural Network “Arjun" Deep Learning Steps 1 and 2 are combined into 1 step. Deep Learning Differences Machine Learning Classifier Algorithm Feature Detection
  • 7. 7 Deep Learning Problem Types Deep Learning can solve multiple supervised and unsupervised problems. • The majority of its success has been when working with images, natural language, and audio data. • Image classification and detection. • Semantic segmentation. • Natural language object retrieval. • Speech recognition and language translation.
  • 8. 8 Classification and Detection Detect and label the image • Person • Motor Bike https://people.eecs.berkeley.edu/~jhoffman/talks/lsda-baylearn2014.pdf
  • 9. 9 Semantic Segmentation Label every pixel https://people.eecs.berkeley.edu/~jhoffman/talks/lsda-baylearn2014.pdf
  • 10. 10 Natural Language Object Retrieval http://arxiv.org/pdf/1511.04164v3.pdf
  • 11. 11 Speech Recognition and Language Translation http://svail.github.io/mandarin/ The same architecture can be used for speech recognition in English, or in Mandarin Chinese.
  • 12.
  • 13. Formulating Supervised Learning Tools 13 For a supervised learning problem: • Collect a labeled dataset (features and target labels). • Choose the model. • Choose an evaluation metric: “What to use to measure performance.” • Choose an optimization method:1 “How to find the model configuration that gives the best performance.” 1 There are standard methods to use for different models and metrics.
  • 14. Which Model? 14 There are many models that represent the problem and make decisions in different ways, each with their own advantages and disadvantages. • DL models are biologically inspired. • The main building block is a neuron. Neuron
  • 15. Neuron 15 A neuron multiplies each feature by a weight and then adds these values together. • Z = X1W1+ X2W2+ X3W3 Z X1 X2 X3 W2 W1 W3
  • 16. Neuron 16 This value is then put through a function called the activation function. • There are several activation functions that can be used. • The output of the neuron is the output of the activation function. Activation Function X1 X2 X3 W2 W1 W3 Output
  • 17. Perceptron 17 A neuron with a simple activation function can solve linearly separable problems. • These are problems where the different classes can be separated by a line. • The Perceptron: one of the earliest neural network models that used neurons with simple activation functions.
  • 18. Perceptron 18 Problems where the labels cannot be separated by a single line are not solvable by a single neuron. • This is a major limitation, and one of the reasons for the first AI winter, that was discussed in lesson 1.
  • 19. 19 Fully Connected Network http://svail.github.io/mandarin/ More complicated problems can be solved by connecting multiple neurons together and using more complicated activation functions. • Organized into layers of neurons. • Each neuron is connected to every neuron in the previous layer. • Each layer transforms the output of the previous layer and then passes it on to the next. • Every connection has a separate weight.
  • 20. Deep Learning Deep Learning refers to when many layers are used to build deep networks. • State-of-the-art models use hundreds of layers. • Deep layers tend to decrease in width. • Successive layers transform inputs with two effects: • Compression: each layer is asked to summarize the input in a way that best serves the task. • Extraction: the model succeeds when each layer extracts task-relevant information. Input Output
  • 21. 21 Steps in Building a Fully Connected Network To build a fully connected network a user needs to: • Define the network architecture. • How many layers and neurons? • Define what activation function to use for each neuron. • Define an evaluation metric. • The values for the weights are learned during model training. http://svail.github.io/mandarin/
  • 22. 22 Evaluation Metric The metric used will depend on the problem being solved. Some examples include: • Regression • Mean Squared Error • Classification • Categorical Cross-Entropy • Multi-Label classification • Binary Cross-Entropy
  • 23. 23 Fully Connected Network Problems Not optimal for detecting features. • Computationally intensive – heavy memory usage.
  • 24.
  • 25. 25 Convolutional Neural Network Convolutional neural networks reduce the required computation and are good for detecting features. • Each neuron is connected to a small set of nearby neurons in the previous layer. • The same set of weights are used for each neuron. • Ideal for spatial feature recognition. • Example: image recognition • Cheaper on resources due to fewer connections. http://svail.github.io/mandarin/
  • 26. 26 Convolutions as Feature Detectors -1 1 -1 -1 1 -1 -1 1 -1 Vertical Line Detector -1 -1 -1 1 1 1 -1 -1 -1 Horizontal Line Detector -1 -1 -1 -1 1 1 -1 1 1 Corner Detector Convolutions can be thought of as “local feature detectors”.
  • 29.
  • 30. 30 Transfer Learning There are difficulties with building convolutional neural networks. • They require huge datasets. • There is a large amount of required computation. • A large amount of time is spent experimenting to get the hyper-parameters correct. • It would be very difficult to train a famous, competition-winning model from scratch
  • 31. 31 Transfer Learning We can take advantage of existing DL models. • Early layers in a neural network are the hardest (slowest) to train. • These ”primitive” features should be general across many image classification tasks. • Later layers in the network capture features that are more particular to the specific image classification problem. • Later layers are easier (quicker) to train since adjusting their weights has a more immediate impact on the final result.
  • 32. 32 Transfer Learning Keeping the early layers of a pre-trained network, and re-training the later layers for a specific application, is called transfer learning. • Results of the training are weights (numbers) that are easy to store. • Using pre-trained layers reduces the amount of required data.
  • 33. 33 Convolutional Neural Network Convolutions Fully Connected Fix Weights Train only the last layer
  • 34. 34 Transfer Learning Options The additional training of a pre-trained network on a specific new dataset is referred to as “fine-tuning”. • Choose “how much” and “how far back” to fine-tune. • Should I train just the very last layer, or go back a few layers? • Re-train the entire network (from the starting-point of the existing network)?
  • 35.
  • 39. 39 MobileNets Efficient models for mobile and embedded vision applications. MobileNet models can be applied to various recognition tasks for efficient device intelligence.
  • 40. 40 Learning Objectives • Identify the types of problems Deep Learning resolves. • Describe the steps in building a neural network model. • Describe a convolutional neural network. • Explain transfer learning and why it’s useful. • Identify common Deep Learning architectures. In this session we worked to:

Hinweis der Redaktion

  1. For some tasks, like image recognition, Deep Learning can eliminate feature extraction.
  2. localize a target object within a given image based on a natural language query of the object. Natural language object retrieval differs from text-based image retrieval task as it involves spatial information about objects within the scene and global scene context
  3. CTC – Connectionist Temporal Classification English – Non tonal language, pitch is not important. So the traditional speech detection systems which convert raw audio to frequency lose out on pitch and work for english. Mandarin – Tonal, so pitch is important. Deep speech does not convert to frequency, so using raw input sound, train the NN for both english and mandarin Traditional speech detection systems extract abstract units of sound (Phonemes), map every word in the vocabulary to a set of phonemes. Adapting this to madarin would require constructing a new lexicon. Deep speech – does not need a new lexicon since the R-CNNs maps variable length speech to characters can adapt equally well to both english and mandarin. Language modelling – how probable is a string of words in a given language. English – words are separated by space, mandarin not. Deep speech uses a character based segmentation. All in all, most significant change is extending the last layer to include more characters in the mandarin language and deep speech works equally well.
  4. We’ll explore this more in this lesson’s assignment.