SlideShare a Scribd company logo
Computational
graphs
Presenters -
Mohamed Aboeleinen
A H M Forhadul Islam
Outline
➔ Computational Graphs
◆ How it works?
◆ Forward and Backward Propagation
➔ TensorFlow as an example
◆ History
◆ Features
◆ Parallelism
◆ Uses and Case Study
➔ CNTK and other tools
◆ Comparison
◆ TensorFlow on Spark
1.
Computational
Graphs
Representation of a composite function
as a network of connected nodes
How it works?
Nodes
They can a math operation or persistent
data.
Flow of data
The Output of each step is an input to the
next.
Edges
They represent the flow of data in the
form multidimensional array.
Forward Propagation and Backward Propagation
Computational Graphs can be used to
show flow of computation, information
always moves one direction; it never
goes backwards.
It could be used to:
● Mimic Brain Activity.
● Model the behaviour of different
models: Social Networks,
Network of Roads.
Backward Propagation
Error Function is propagated backwards
adjusting the weights and biases to
minimize the cost, learning process. (the
fundamental concept of Machine
Learning)
2.
TensorFlow
Numerical computation using data flow
graphs
History
2011
Nov.,
2015
Andrew Ng of Stanford alongside Jeff Dean and Greg
Corrado of Google started to build a large-scale deep
learning software system “DistBelief”
Google releases an open source version of
Tensor Flow.
May,
2016
Google announces its tensor flow
tailored ASIC (TPU).
And now this!
https://youtu.be/-F-TQJtbFMs
TF!
Main features
No change over platforms For
example: phones and tablets up
to large-scale distributed and
thousands of computational
devices such as GPU cards.
Flexible, can be used for a lot of
algorithms
Used in a lot of applications: NLP,
Robotics, Drug Discovery, Speech
Recognition
ٍٍSuports parallelism.
Data Parallelism
Different subsets of data are used
on different nodes in a cluster,
followed by parameter averaging
and replacement across the cluster
Model Parallelism
Different parts of the model are
trained in different devices.
Example: Train stacked RNN by
deploying each RNN on a different
device
Parallelism in TensorFlow ( Distributed TensorFlow )
“
“When you train a model you use
variables to hold and update parameters.
Variables are in-memory buffers
containing tensors”
Support
◎ Tensorflow supports Python and C++
◎ Even horizontal scaling using gRPC.
◎ CPU, GPU, CUDA
◎ Convolutional neural network (CNN)
◎ Recurrent neural network (RNN)
◎ Long short-term memory (LSTM)
TensorFlow Uses
RankBrain
Org: Google
Task: Information
Retrieval
A large-scale
deployment of deep
neural nets for search
ranking on google.com
Massively Multitask
Networks for Drug
Discovery
Org: Stanford and
Google
Task: Drug discovery
A deep neural network
model for identifying
promising drug
candidates
On-Device
Computer Vision
for OCR
Org: Google
Task: Translation
On-device computer
vision model to do
optical character
recognition to enable
real-time translation.
Tensor Flow in
Medicine:
Retinal Imaging
Case Study
Case Study: Tensor Flow in Medicine
Retinal Imaging Project by Lily Peng, MD, PHD of Google.
● Diabetic retinopathy is the fastest growing cause of
blindness in the world.
● All diabetic patients (more than 400 M) have to
checked yearly to detect a DR patient before it is
too late to intervene.
Image Courtesy: Google 2017 Development Summit slides.
Is it still a good idea to go to the doctor?
● Even if the doctor is available, there is a high chance for a the
intolerable false negative.
None
Mild
Moderate
Severe
Proliferative
Image Courtesy: Google 2017 Development Summit slides.
How did TensorFlow help?
● Easier for non-deep learning experts to implement and prototype.
● Hardware Support (GPU for example)
● Moves the challenge from the modeling and training to finding the
right problem, getting the data and consent, validation and
deployment.
Image Courtesy: Google 2017 Development Summit slides.
Place your screenshot here
TensorBoard
Visualization of graph structures and summary statistics.
2.
CNTK (Cognitive Toolkit)
An unified deep-learning toolkit that
describes neural networks as a series of
computational steps by a directed
graph
+ Points
Open
Source
❤
Free
No Ads
CNTK!
◎ At the very core of CNTK is the
Compute graph.
◎ Each CNTK compute graph is
comprised of a set of nodes
where each node represents a
key mathematical operation
◎ The edges between nodes in
the graph represent data flow
between operations
◎ ٍٍSuports GPU/multi-server.
CNTK benchmark
In the benchmark published, it seems a very powerful
tool for vertical and horizontal scaling.
3 main tasks ( TED )
Train
Define a network and train it to produce a
trained model using training data
Evaluate
Test a trained model to assess its performance
using test data
Deploy
Use a trained model, e.g. in your own solution,
to classify new instances
Uber is using driver
selfies to enhance
security, powered
by Microsoft
Cognitive Services
Emotion API
{
"faceRectangle": {
"left": 732,
"top": 201,
"width": 191,
"height": 191
},
"scores": {
"anger": 0.0000262709273,
"contempt": 0.0000356922574,
"disgust": 0.0000494521,
"fear": 0.000004611067,
"happiness": 0.999419332,
"neutral": 0.00043529534,
"sadness": 0.00000680253424,
"surprise": 0.0000225645144
}
…...
Voice recognition
Motion Detection
Face detection and tracking
Language checking ( speaking )
Speaker recognition
6,500,000Files were tested
2.94%Family error rate!
0.358 %
Error rate
MtNet was trained (labeled data)
MtNet, is a new deep learning malware classification architecture
Tensorflow Vs. Torche Vs. Theano
Marketing itself
Tensorflow got the lead that would
result in stronger community of users
and faster development.
Entities’ support
Tensorflow has got Google, while
Theano is still supported by University
of Montreal. Torch supported by
Facebook, twitter and NVIDIA!
Visualizations
Tensorflow has better computational
graph visualizations but for Images
and Graphs Theano is as good.
Debugging
Torch “automatic differentiation” is
better for debugging than Theano
and TensorFlow “symbolic
computation”.
Large-Scale
Machine Learning
How to train big model
over big data?
TensorFlowOnSpark
❏ Combines salient features from deep learning
framework TensorFlow and big-data frameworks
Apache Spark and Apache Hadoop
❏
Honourable mentions
DL4J
DeepLearning4J
Seeing AI project
https://youtu.be/R2mC-NUAmMk
References
◎ Abadi, Martín, et al. "Tensorflow: Large-scale machine learning on
heterogeneous distributed systems." arXiv preprint arXiv:1603.04467 (2016).
◎ Looks, Moshe, et al. "Deep learning with dynamic computation graphs." arXiv
preprint arXiv:1702.02181 (2017).
◎ https://www.slideshare.net/MiguelFierro1/leveraging-deep-learning-applic
ations-with-cntk
◎ https://www.slideshare.net/JeffreyShomaker/deep-learning-jeffshomaker12
017final
◎ PyTorch, Dynamic Computational Graphs and Modular Deep Learning - Carlos
Perez
◎ https://github.com/Microsoft/CNTK
◎ https://medium.com/@ricardo.guerrero/deep-learning-frameworks-a-revi
ew-before-finishing-2016-5b3ab4010b06
◎ https://cs224d.stanford.edu/lectures/CS224d-Lecture7.pdf
◎ https://www.packtpub.com/books/content/getting-started-deep-learning
◎ https://leonardoaraujosantos.gitbooks.io/artificial-inteligence/content/tenso
rflow.html
◎ https://github.com/yahoo/TensorFlowOnSpark
◎ http://www.dmtk.io/slides/distributedML-aaai2017.pdf
Questions?
Thank you

More Related Content

What's hot

Deep learning at nmc devin jones
Deep learning at nmc devin jones Deep learning at nmc devin jones
Deep learning at nmc devin jones
Ido Shilon
 
Deep learning with tensorflow
Deep learning with tensorflowDeep learning with tensorflow
Deep learning with tensorflow
Charmi Chokshi
 
Data Parallel Deep Learning
Data Parallel Deep LearningData Parallel Deep Learning
Data Parallel Deep Learning
inside-BigData.com
 
"Large-Scale Deep Learning for Building Intelligent Computer Systems," a Keyn...
"Large-Scale Deep Learning for Building Intelligent Computer Systems," a Keyn..."Large-Scale Deep Learning for Building Intelligent Computer Systems," a Keyn...
"Large-Scale Deep Learning for Building Intelligent Computer Systems," a Keyn...
Edge AI and Vision Alliance
 
Automating Machine Learning - Is it feasible?
Automating Machine Learning - Is it feasible?Automating Machine Learning - Is it feasible?
Automating Machine Learning - Is it feasible?
Manuel Martín
 
Machine learning_ Replicating Human Brain
Machine learning_ Replicating Human BrainMachine learning_ Replicating Human Brain
Machine learning_ Replicating Human Brain
Nishant Jain
 
Using Deep Learning to Find Similar Dresses
Using Deep Learning to Find Similar DressesUsing Deep Learning to Find Similar Dresses
Using Deep Learning to Find Similar Dresses
HJ van Veen
 
A Friendly Introduction to Machine Learning
A Friendly Introduction to Machine LearningA Friendly Introduction to Machine Learning
A Friendly Introduction to Machine Learning
Haptik
 
Artificial Intelligence = ML + DL with Tensor Flow
Artificial Intelligence = ML + DL with Tensor FlowArtificial Intelligence = ML + DL with Tensor Flow
Introduction to Machine Learning
Introduction to Machine LearningIntroduction to Machine Learning
Introduction to Machine Learning
Nandita Naik
 
Bol.com
Bol.comBol.com
Bol.com
BigDataExpo
 
Anomaly Detection using Deep Auto-Encoders | Gianmario Spacagna
Anomaly Detection using Deep Auto-Encoders | Gianmario SpacagnaAnomaly Detection using Deep Auto-Encoders | Gianmario Spacagna
Anomaly Detection using Deep Auto-Encoders | Gianmario Spacagna
Data Science Milan
 
Deep learning crash course
Deep learning crash courseDeep learning crash course
Deep learning crash course
Vishwas N
 
Machine Learning Overview
Machine Learning OverviewMachine Learning Overview
Machine Learning Overview
Mykhailo Koval
 
Basic image analysis(processing and classification) and visualization using m...
Basic image analysis(processing and classification) and visualization using m...Basic image analysis(processing and classification) and visualization using m...
Basic image analysis(processing and classification) and visualization using m...
Vishwas N
 
An overview of machine learning
An overview of machine learningAn overview of machine learning
An overview of machine learning
drcfetr
 
Deep Learning Primer: A First-Principles Approach
Deep Learning Primer: A First-Principles ApproachDeep Learning Primer: A First-Principles Approach
Deep Learning Primer: A First-Principles Approach
Maurizio Calo Caligaris
 
“Introducing Machine Learning and How to Teach Machines to See,” a Presentati...
“Introducing Machine Learning and How to Teach Machines to See,” a Presentati...“Introducing Machine Learning and How to Teach Machines to See,” a Presentati...
“Introducing Machine Learning and How to Teach Machines to See,” a Presentati...
Edge AI and Vision Alliance
 
Image anomaly detection with generative adversarial networks
Image anomaly detection with generative adversarial networksImage anomaly detection with generative adversarial networks
Image anomaly detection with generative adversarial networks
SakshiSingh480
 
Introduction to machine learning
Introduction to machine learningIntroduction to machine learning
Introduction to machine learning
Pruet Boonma
 

What's hot (20)

Deep learning at nmc devin jones
Deep learning at nmc devin jones Deep learning at nmc devin jones
Deep learning at nmc devin jones
 
Deep learning with tensorflow
Deep learning with tensorflowDeep learning with tensorflow
Deep learning with tensorflow
 
Data Parallel Deep Learning
Data Parallel Deep LearningData Parallel Deep Learning
Data Parallel Deep Learning
 
"Large-Scale Deep Learning for Building Intelligent Computer Systems," a Keyn...
"Large-Scale Deep Learning for Building Intelligent Computer Systems," a Keyn..."Large-Scale Deep Learning for Building Intelligent Computer Systems," a Keyn...
"Large-Scale Deep Learning for Building Intelligent Computer Systems," a Keyn...
 
Automating Machine Learning - Is it feasible?
Automating Machine Learning - Is it feasible?Automating Machine Learning - Is it feasible?
Automating Machine Learning - Is it feasible?
 
Machine learning_ Replicating Human Brain
Machine learning_ Replicating Human BrainMachine learning_ Replicating Human Brain
Machine learning_ Replicating Human Brain
 
Using Deep Learning to Find Similar Dresses
Using Deep Learning to Find Similar DressesUsing Deep Learning to Find Similar Dresses
Using Deep Learning to Find Similar Dresses
 
A Friendly Introduction to Machine Learning
A Friendly Introduction to Machine LearningA Friendly Introduction to Machine Learning
A Friendly Introduction to Machine Learning
 
Artificial Intelligence = ML + DL with Tensor Flow
Artificial Intelligence = ML + DL with Tensor FlowArtificial Intelligence = ML + DL with Tensor Flow
Artificial Intelligence = ML + DL with Tensor Flow
 
Introduction to Machine Learning
Introduction to Machine LearningIntroduction to Machine Learning
Introduction to Machine Learning
 
Bol.com
Bol.comBol.com
Bol.com
 
Anomaly Detection using Deep Auto-Encoders | Gianmario Spacagna
Anomaly Detection using Deep Auto-Encoders | Gianmario SpacagnaAnomaly Detection using Deep Auto-Encoders | Gianmario Spacagna
Anomaly Detection using Deep Auto-Encoders | Gianmario Spacagna
 
Deep learning crash course
Deep learning crash courseDeep learning crash course
Deep learning crash course
 
Machine Learning Overview
Machine Learning OverviewMachine Learning Overview
Machine Learning Overview
 
Basic image analysis(processing and classification) and visualization using m...
Basic image analysis(processing and classification) and visualization using m...Basic image analysis(processing and classification) and visualization using m...
Basic image analysis(processing and classification) and visualization using m...
 
An overview of machine learning
An overview of machine learningAn overview of machine learning
An overview of machine learning
 
Deep Learning Primer: A First-Principles Approach
Deep Learning Primer: A First-Principles ApproachDeep Learning Primer: A First-Principles Approach
Deep Learning Primer: A First-Principles Approach
 
“Introducing Machine Learning and How to Teach Machines to See,” a Presentati...
“Introducing Machine Learning and How to Teach Machines to See,” a Presentati...“Introducing Machine Learning and How to Teach Machines to See,” a Presentati...
“Introducing Machine Learning and How to Teach Machines to See,” a Presentati...
 
Image anomaly detection with generative adversarial networks
Image anomaly detection with generative adversarial networksImage anomaly detection with generative adversarial networks
Image anomaly detection with generative adversarial networks
 
Introduction to machine learning
Introduction to machine learningIntroduction to machine learning
Introduction to machine learning
 

Similar to Computation graphs - Tensorflow & CNTK

AI and Deep Learning
AI and Deep Learning AI and Deep Learning
AI and Deep Learning
Subrat Panda, PhD
 
Neuromation.io AI Ukraine Presentation
Neuromation.io AI Ukraine PresentationNeuromation.io AI Ukraine Presentation
Neuromation.io AI Ukraine Presentation
Bohdan Klimenko
 
Using Neural Net Algorithms to Classify Human Activity, with Applications in ...
Using Neural Net Algorithms to Classify Human Activity, with Applications in ...Using Neural Net Algorithms to Classify Human Activity, with Applications in ...
Using Neural Net Algorithms to Classify Human Activity, with Applications in ...
Rohan Karunaratne
 
Transfer Leaning Using Pytorch synopsis Minor project pptx
Transfer Leaning Using Pytorch  synopsis Minor project pptxTransfer Leaning Using Pytorch  synopsis Minor project pptx
Transfer Leaning Using Pytorch synopsis Minor project pptx
Ankit Gupta
 
Model Evaluation in the land of Deep Learning
Model Evaluation in the land of Deep LearningModel Evaluation in the land of Deep Learning
Model Evaluation in the land of Deep Learning
Pramit Choudhary
 
Deep Learning Demystified
Deep Learning DemystifiedDeep Learning Demystified
Deep Learning Demystified
Affine Analytics
 
building intelligent systems with large scale deep learning
building intelligent systems with large scale deep learningbuilding intelligent systems with large scale deep learning
building intelligent systems with large scale deep learning
mustafa sarac
 
Large Scale Deep Learning with TensorFlow
Large Scale Deep Learning with TensorFlow Large Scale Deep Learning with TensorFlow
Large Scale Deep Learning with TensorFlow
Jen Aman
 
Performance Comparison between Pytorch and Mindspore
Performance Comparison between Pytorch and MindsporePerformance Comparison between Pytorch and Mindspore
Performance Comparison between Pytorch and Mindspore
ijdms
 
Deep Learning With Neural Networks
Deep Learning With Neural NetworksDeep Learning With Neural Networks
Deep Learning With Neural Networks
Aniket Maurya
 
Persian MNIST in 5 Minutes
Persian MNIST in 5 MinutesPersian MNIST in 5 Minutes
Persian MNIST in 5 Minutes
Shahriar Yazdipour
 
Scaling AI in production using PyTorch
Scaling AI in production using PyTorchScaling AI in production using PyTorch
Scaling AI in production using PyTorch
geetachauhan
 
Machine learning
 Machine learning Machine learning
Machine learning
Siddharth Kar
 
SPEED-UP IMPROVEMENT USING PARALLEL APPROACH IN IMAGE STEGANOGRAPHY
SPEED-UP IMPROVEMENT USING PARALLEL APPROACH IN IMAGE STEGANOGRAPHYSPEED-UP IMPROVEMENT USING PARALLEL APPROACH IN IMAGE STEGANOGRAPHY
SPEED-UP IMPROVEMENT USING PARALLEL APPROACH IN IMAGE STEGANOGRAPHY
csandit
 
Synergy of Human and Artificial Intelligence in Software Engineering
Synergy of Human and Artificial Intelligence in Software EngineeringSynergy of Human and Artificial Intelligence in Software Engineering
Synergy of Human and Artificial Intelligence in Software Engineering
Tao Xie
 
Koss 1605 machine_learning_mariocho_t10
Koss 1605 machine_learning_mariocho_t10Koss 1605 machine_learning_mariocho_t10
Koss 1605 machine_learning_mariocho_t10
Mario Cho
 
Development of 3D convolutional neural network to recognize human activities ...
Development of 3D convolutional neural network to recognize human activities ...Development of 3D convolutional neural network to recognize human activities ...
Development of 3D convolutional neural network to recognize human activities ...
journalBEEI
 
Cognitive Toolkit - Deep Learning framework from Microsoft
Cognitive Toolkit - Deep Learning framework from MicrosoftCognitive Toolkit - Deep Learning framework from Microsoft
Cognitive Toolkit - Deep Learning framework from Microsoft
Łukasz Grala
 
Tensorflow
TensorflowTensorflow
Tensorflow
marwa Ayad Mohamed
 
AI in the Financial Services Industry
AI in the Financial Services IndustryAI in the Financial Services Industry
AI in the Financial Services Industry
Alison B. Lowndes
 

Similar to Computation graphs - Tensorflow & CNTK (20)

AI and Deep Learning
AI and Deep Learning AI and Deep Learning
AI and Deep Learning
 
Neuromation.io AI Ukraine Presentation
Neuromation.io AI Ukraine PresentationNeuromation.io AI Ukraine Presentation
Neuromation.io AI Ukraine Presentation
 
Using Neural Net Algorithms to Classify Human Activity, with Applications in ...
Using Neural Net Algorithms to Classify Human Activity, with Applications in ...Using Neural Net Algorithms to Classify Human Activity, with Applications in ...
Using Neural Net Algorithms to Classify Human Activity, with Applications in ...
 
Transfer Leaning Using Pytorch synopsis Minor project pptx
Transfer Leaning Using Pytorch  synopsis Minor project pptxTransfer Leaning Using Pytorch  synopsis Minor project pptx
Transfer Leaning Using Pytorch synopsis Minor project pptx
 
Model Evaluation in the land of Deep Learning
Model Evaluation in the land of Deep LearningModel Evaluation in the land of Deep Learning
Model Evaluation in the land of Deep Learning
 
Deep Learning Demystified
Deep Learning DemystifiedDeep Learning Demystified
Deep Learning Demystified
 
building intelligent systems with large scale deep learning
building intelligent systems with large scale deep learningbuilding intelligent systems with large scale deep learning
building intelligent systems with large scale deep learning
 
Large Scale Deep Learning with TensorFlow
Large Scale Deep Learning with TensorFlow Large Scale Deep Learning with TensorFlow
Large Scale Deep Learning with TensorFlow
 
Performance Comparison between Pytorch and Mindspore
Performance Comparison between Pytorch and MindsporePerformance Comparison between Pytorch and Mindspore
Performance Comparison between Pytorch and Mindspore
 
Deep Learning With Neural Networks
Deep Learning With Neural NetworksDeep Learning With Neural Networks
Deep Learning With Neural Networks
 
Persian MNIST in 5 Minutes
Persian MNIST in 5 MinutesPersian MNIST in 5 Minutes
Persian MNIST in 5 Minutes
 
Scaling AI in production using PyTorch
Scaling AI in production using PyTorchScaling AI in production using PyTorch
Scaling AI in production using PyTorch
 
Machine learning
 Machine learning Machine learning
Machine learning
 
SPEED-UP IMPROVEMENT USING PARALLEL APPROACH IN IMAGE STEGANOGRAPHY
SPEED-UP IMPROVEMENT USING PARALLEL APPROACH IN IMAGE STEGANOGRAPHYSPEED-UP IMPROVEMENT USING PARALLEL APPROACH IN IMAGE STEGANOGRAPHY
SPEED-UP IMPROVEMENT USING PARALLEL APPROACH IN IMAGE STEGANOGRAPHY
 
Synergy of Human and Artificial Intelligence in Software Engineering
Synergy of Human and Artificial Intelligence in Software EngineeringSynergy of Human and Artificial Intelligence in Software Engineering
Synergy of Human and Artificial Intelligence in Software Engineering
 
Koss 1605 machine_learning_mariocho_t10
Koss 1605 machine_learning_mariocho_t10Koss 1605 machine_learning_mariocho_t10
Koss 1605 machine_learning_mariocho_t10
 
Development of 3D convolutional neural network to recognize human activities ...
Development of 3D convolutional neural network to recognize human activities ...Development of 3D convolutional neural network to recognize human activities ...
Development of 3D convolutional neural network to recognize human activities ...
 
Cognitive Toolkit - Deep Learning framework from Microsoft
Cognitive Toolkit - Deep Learning framework from MicrosoftCognitive Toolkit - Deep Learning framework from Microsoft
Cognitive Toolkit - Deep Learning framework from Microsoft
 
Tensorflow
TensorflowTensorflow
Tensorflow
 
AI in the Financial Services Industry
AI in the Financial Services IndustryAI in the Financial Services Industry
AI in the Financial Services Industry
 

Recently uploaded

Observability Concepts EVERY Developer Should Know -- DeveloperWeek Europe.pdf
Observability Concepts EVERY Developer Should Know -- DeveloperWeek Europe.pdfObservability Concepts EVERY Developer Should Know -- DeveloperWeek Europe.pdf
Observability Concepts EVERY Developer Should Know -- DeveloperWeek Europe.pdf
Paige Cruz
 
GenAI Pilot Implementation in the organizations
GenAI Pilot Implementation in the organizationsGenAI Pilot Implementation in the organizations
GenAI Pilot Implementation in the organizations
kumardaparthi1024
 
Why You Should Replace Windows 11 with Nitrux Linux 3.5.0 for enhanced perfor...
Why You Should Replace Windows 11 with Nitrux Linux 3.5.0 for enhanced perfor...Why You Should Replace Windows 11 with Nitrux Linux 3.5.0 for enhanced perfor...
Why You Should Replace Windows 11 with Nitrux Linux 3.5.0 for enhanced perfor...
SOFTTECHHUB
 
Introduction to CHERI technology - Cybersecurity
Introduction to CHERI technology - CybersecurityIntroduction to CHERI technology - Cybersecurity
Introduction to CHERI technology - Cybersecurity
mikeeftimakis1
 
みなさんこんにちはこれ何文字まで入るの?40文字以下不可とか本当に意味わからないけどこれ限界文字数書いてないからマジでやばい文字数いけるんじゃないの?えこ...
みなさんこんにちはこれ何文字まで入るの?40文字以下不可とか本当に意味わからないけどこれ限界文字数書いてないからマジでやばい文字数いけるんじゃないの?えこ...みなさんこんにちはこれ何文字まで入るの?40文字以下不可とか本当に意味わからないけどこれ限界文字数書いてないからマジでやばい文字数いけるんじゃないの?えこ...
みなさんこんにちはこれ何文字まで入るの?40文字以下不可とか本当に意味わからないけどこれ限界文字数書いてないからマジでやばい文字数いけるんじゃないの?えこ...
名前 です男
 
Driving Business Innovation: Latest Generative AI Advancements & Success Story
Driving Business Innovation: Latest Generative AI Advancements & Success StoryDriving Business Innovation: Latest Generative AI Advancements & Success Story
Driving Business Innovation: Latest Generative AI Advancements & Success Story
Safe Software
 
UiPath Test Automation using UiPath Test Suite series, part 5
UiPath Test Automation using UiPath Test Suite series, part 5UiPath Test Automation using UiPath Test Suite series, part 5
UiPath Test Automation using UiPath Test Suite series, part 5
DianaGray10
 
TrustArc Webinar - 2024 Global Privacy Survey
TrustArc Webinar - 2024 Global Privacy SurveyTrustArc Webinar - 2024 Global Privacy Survey
TrustArc Webinar - 2024 Global Privacy Survey
TrustArc
 
“I’m still / I’m still / Chaining from the Block”
“I’m still / I’m still / Chaining from the Block”“I’m still / I’m still / Chaining from the Block”
“I’m still / I’m still / Chaining from the Block”
Claudio Di Ciccio
 
GraphSummit Singapore | Graphing Success: Revolutionising Organisational Stru...
GraphSummit Singapore | Graphing Success: Revolutionising Organisational Stru...GraphSummit Singapore | Graphing Success: Revolutionising Organisational Stru...
GraphSummit Singapore | Graphing Success: Revolutionising Organisational Stru...
Neo4j
 
Artificial Intelligence for XMLDevelopment
Artificial Intelligence for XMLDevelopmentArtificial Intelligence for XMLDevelopment
Artificial Intelligence for XMLDevelopment
Octavian Nadolu
 
Infrastructure Challenges in Scaling RAG with Custom AI models
Infrastructure Challenges in Scaling RAG with Custom AI modelsInfrastructure Challenges in Scaling RAG with Custom AI models
Infrastructure Challenges in Scaling RAG with Custom AI models
Zilliz
 
Programming Foundation Models with DSPy - Meetup Slides
Programming Foundation Models with DSPy - Meetup SlidesProgramming Foundation Models with DSPy - Meetup Slides
Programming Foundation Models with DSPy - Meetup Slides
Zilliz
 
20240605 QFM017 Machine Intelligence Reading List May 2024
20240605 QFM017 Machine Intelligence Reading List May 202420240605 QFM017 Machine Intelligence Reading List May 2024
20240605 QFM017 Machine Intelligence Reading List May 2024
Matthew Sinclair
 
GraphSummit Singapore | Enhancing Changi Airport Group's Passenger Experience...
GraphSummit Singapore | Enhancing Changi Airport Group's Passenger Experience...GraphSummit Singapore | Enhancing Changi Airport Group's Passenger Experience...
GraphSummit Singapore | Enhancing Changi Airport Group's Passenger Experience...
Neo4j
 
Video Streaming: Then, Now, and in the Future
Video Streaming: Then, Now, and in the FutureVideo Streaming: Then, Now, and in the Future
Video Streaming: Then, Now, and in the Future
Alpen-Adria-Universität
 
How to use Firebase Data Connect For Flutter
How to use Firebase Data Connect For FlutterHow to use Firebase Data Connect For Flutter
How to use Firebase Data Connect For Flutter
Daiki Mogmet Ito
 
Mariano G Tinti - Decoding SpaceX
Mariano G Tinti - Decoding SpaceXMariano G Tinti - Decoding SpaceX
Mariano G Tinti - Decoding SpaceX
Mariano Tinti
 
Unlock the Future of Search with MongoDB Atlas_ Vector Search Unleashed.pdf
Unlock the Future of Search with MongoDB Atlas_ Vector Search Unleashed.pdfUnlock the Future of Search with MongoDB Atlas_ Vector Search Unleashed.pdf
Unlock the Future of Search with MongoDB Atlas_ Vector Search Unleashed.pdf
Malak Abu Hammad
 
Mind map of terminologies used in context of Generative AI
Mind map of terminologies used in context of Generative AIMind map of terminologies used in context of Generative AI
Mind map of terminologies used in context of Generative AI
Kumud Singh
 

Recently uploaded (20)

Observability Concepts EVERY Developer Should Know -- DeveloperWeek Europe.pdf
Observability Concepts EVERY Developer Should Know -- DeveloperWeek Europe.pdfObservability Concepts EVERY Developer Should Know -- DeveloperWeek Europe.pdf
Observability Concepts EVERY Developer Should Know -- DeveloperWeek Europe.pdf
 
GenAI Pilot Implementation in the organizations
GenAI Pilot Implementation in the organizationsGenAI Pilot Implementation in the organizations
GenAI Pilot Implementation in the organizations
 
Why You Should Replace Windows 11 with Nitrux Linux 3.5.0 for enhanced perfor...
Why You Should Replace Windows 11 with Nitrux Linux 3.5.0 for enhanced perfor...Why You Should Replace Windows 11 with Nitrux Linux 3.5.0 for enhanced perfor...
Why You Should Replace Windows 11 with Nitrux Linux 3.5.0 for enhanced perfor...
 
Introduction to CHERI technology - Cybersecurity
Introduction to CHERI technology - CybersecurityIntroduction to CHERI technology - Cybersecurity
Introduction to CHERI technology - Cybersecurity
 
みなさんこんにちはこれ何文字まで入るの?40文字以下不可とか本当に意味わからないけどこれ限界文字数書いてないからマジでやばい文字数いけるんじゃないの?えこ...
みなさんこんにちはこれ何文字まで入るの?40文字以下不可とか本当に意味わからないけどこれ限界文字数書いてないからマジでやばい文字数いけるんじゃないの?えこ...みなさんこんにちはこれ何文字まで入るの?40文字以下不可とか本当に意味わからないけどこれ限界文字数書いてないからマジでやばい文字数いけるんじゃないの?えこ...
みなさんこんにちはこれ何文字まで入るの?40文字以下不可とか本当に意味わからないけどこれ限界文字数書いてないからマジでやばい文字数いけるんじゃないの?えこ...
 
Driving Business Innovation: Latest Generative AI Advancements & Success Story
Driving Business Innovation: Latest Generative AI Advancements & Success StoryDriving Business Innovation: Latest Generative AI Advancements & Success Story
Driving Business Innovation: Latest Generative AI Advancements & Success Story
 
UiPath Test Automation using UiPath Test Suite series, part 5
UiPath Test Automation using UiPath Test Suite series, part 5UiPath Test Automation using UiPath Test Suite series, part 5
UiPath Test Automation using UiPath Test Suite series, part 5
 
TrustArc Webinar - 2024 Global Privacy Survey
TrustArc Webinar - 2024 Global Privacy SurveyTrustArc Webinar - 2024 Global Privacy Survey
TrustArc Webinar - 2024 Global Privacy Survey
 
“I’m still / I’m still / Chaining from the Block”
“I’m still / I’m still / Chaining from the Block”“I’m still / I’m still / Chaining from the Block”
“I’m still / I’m still / Chaining from the Block”
 
GraphSummit Singapore | Graphing Success: Revolutionising Organisational Stru...
GraphSummit Singapore | Graphing Success: Revolutionising Organisational Stru...GraphSummit Singapore | Graphing Success: Revolutionising Organisational Stru...
GraphSummit Singapore | Graphing Success: Revolutionising Organisational Stru...
 
Artificial Intelligence for XMLDevelopment
Artificial Intelligence for XMLDevelopmentArtificial Intelligence for XMLDevelopment
Artificial Intelligence for XMLDevelopment
 
Infrastructure Challenges in Scaling RAG with Custom AI models
Infrastructure Challenges in Scaling RAG with Custom AI modelsInfrastructure Challenges in Scaling RAG with Custom AI models
Infrastructure Challenges in Scaling RAG with Custom AI models
 
Programming Foundation Models with DSPy - Meetup Slides
Programming Foundation Models with DSPy - Meetup SlidesProgramming Foundation Models with DSPy - Meetup Slides
Programming Foundation Models with DSPy - Meetup Slides
 
20240605 QFM017 Machine Intelligence Reading List May 2024
20240605 QFM017 Machine Intelligence Reading List May 202420240605 QFM017 Machine Intelligence Reading List May 2024
20240605 QFM017 Machine Intelligence Reading List May 2024
 
GraphSummit Singapore | Enhancing Changi Airport Group's Passenger Experience...
GraphSummit Singapore | Enhancing Changi Airport Group's Passenger Experience...GraphSummit Singapore | Enhancing Changi Airport Group's Passenger Experience...
GraphSummit Singapore | Enhancing Changi Airport Group's Passenger Experience...
 
Video Streaming: Then, Now, and in the Future
Video Streaming: Then, Now, and in the FutureVideo Streaming: Then, Now, and in the Future
Video Streaming: Then, Now, and in the Future
 
How to use Firebase Data Connect For Flutter
How to use Firebase Data Connect For FlutterHow to use Firebase Data Connect For Flutter
How to use Firebase Data Connect For Flutter
 
Mariano G Tinti - Decoding SpaceX
Mariano G Tinti - Decoding SpaceXMariano G Tinti - Decoding SpaceX
Mariano G Tinti - Decoding SpaceX
 
Unlock the Future of Search with MongoDB Atlas_ Vector Search Unleashed.pdf
Unlock the Future of Search with MongoDB Atlas_ Vector Search Unleashed.pdfUnlock the Future of Search with MongoDB Atlas_ Vector Search Unleashed.pdf
Unlock the Future of Search with MongoDB Atlas_ Vector Search Unleashed.pdf
 
Mind map of terminologies used in context of Generative AI
Mind map of terminologies used in context of Generative AIMind map of terminologies used in context of Generative AI
Mind map of terminologies used in context of Generative AI
 

Computation graphs - Tensorflow & CNTK

  • 2. Outline ➔ Computational Graphs ◆ How it works? ◆ Forward and Backward Propagation ➔ TensorFlow as an example ◆ History ◆ Features ◆ Parallelism ◆ Uses and Case Study ➔ CNTK and other tools ◆ Comparison ◆ TensorFlow on Spark
  • 3. 1. Computational Graphs Representation of a composite function as a network of connected nodes
  • 4. How it works? Nodes They can a math operation or persistent data. Flow of data The Output of each step is an input to the next. Edges They represent the flow of data in the form multidimensional array.
  • 5. Forward Propagation and Backward Propagation Computational Graphs can be used to show flow of computation, information always moves one direction; it never goes backwards. It could be used to: ● Mimic Brain Activity. ● Model the behaviour of different models: Social Networks, Network of Roads. Backward Propagation Error Function is propagated backwards adjusting the weights and biases to minimize the cost, learning process. (the fundamental concept of Machine Learning)
  • 7. History 2011 Nov., 2015 Andrew Ng of Stanford alongside Jeff Dean and Greg Corrado of Google started to build a large-scale deep learning software system “DistBelief” Google releases an open source version of Tensor Flow. May, 2016 Google announces its tensor flow tailored ASIC (TPU).
  • 9. TF! Main features No change over platforms For example: phones and tablets up to large-scale distributed and thousands of computational devices such as GPU cards. Flexible, can be used for a lot of algorithms Used in a lot of applications: NLP, Robotics, Drug Discovery, Speech Recognition ٍٍSuports parallelism.
  • 10. Data Parallelism Different subsets of data are used on different nodes in a cluster, followed by parameter averaging and replacement across the cluster Model Parallelism Different parts of the model are trained in different devices. Example: Train stacked RNN by deploying each RNN on a different device Parallelism in TensorFlow ( Distributed TensorFlow )
  • 11. “ “When you train a model you use variables to hold and update parameters. Variables are in-memory buffers containing tensors”
  • 12. Support ◎ Tensorflow supports Python and C++ ◎ Even horizontal scaling using gRPC. ◎ CPU, GPU, CUDA ◎ Convolutional neural network (CNN) ◎ Recurrent neural network (RNN) ◎ Long short-term memory (LSTM)
  • 13. TensorFlow Uses RankBrain Org: Google Task: Information Retrieval A large-scale deployment of deep neural nets for search ranking on google.com Massively Multitask Networks for Drug Discovery Org: Stanford and Google Task: Drug discovery A deep neural network model for identifying promising drug candidates On-Device Computer Vision for OCR Org: Google Task: Translation On-device computer vision model to do optical character recognition to enable real-time translation.
  • 14. Tensor Flow in Medicine: Retinal Imaging Case Study
  • 15. Case Study: Tensor Flow in Medicine Retinal Imaging Project by Lily Peng, MD, PHD of Google. ● Diabetic retinopathy is the fastest growing cause of blindness in the world. ● All diabetic patients (more than 400 M) have to checked yearly to detect a DR patient before it is too late to intervene. Image Courtesy: Google 2017 Development Summit slides.
  • 16. Is it still a good idea to go to the doctor? ● Even if the doctor is available, there is a high chance for a the intolerable false negative. None Mild Moderate Severe Proliferative Image Courtesy: Google 2017 Development Summit slides.
  • 17. How did TensorFlow help? ● Easier for non-deep learning experts to implement and prototype. ● Hardware Support (GPU for example) ● Moves the challenge from the modeling and training to finding the right problem, getting the data and consent, validation and deployment. Image Courtesy: Google 2017 Development Summit slides.
  • 18. Place your screenshot here TensorBoard Visualization of graph structures and summary statistics.
  • 19. 2. CNTK (Cognitive Toolkit) An unified deep-learning toolkit that describes neural networks as a series of computational steps by a directed graph
  • 21. CNTK! ◎ At the very core of CNTK is the Compute graph. ◎ Each CNTK compute graph is comprised of a set of nodes where each node represents a key mathematical operation ◎ The edges between nodes in the graph represent data flow between operations ◎ ٍٍSuports GPU/multi-server.
  • 22. CNTK benchmark In the benchmark published, it seems a very powerful tool for vertical and horizontal scaling.
  • 23. 3 main tasks ( TED ) Train Define a network and train it to produce a trained model using training data Evaluate Test a trained model to assess its performance using test data Deploy Use a trained model, e.g. in your own solution, to classify new instances
  • 24. Uber is using driver selfies to enhance security, powered by Microsoft Cognitive Services
  • 25. Emotion API { "faceRectangle": { "left": 732, "top": 201, "width": 191, "height": 191 }, "scores": { "anger": 0.0000262709273, "contempt": 0.0000356922574, "disgust": 0.0000494521, "fear": 0.000004611067, "happiness": 0.999419332, "neutral": 0.00043529534, "sadness": 0.00000680253424, "surprise": 0.0000225645144 } …...
  • 26. Voice recognition Motion Detection Face detection and tracking Language checking ( speaking ) Speaker recognition
  • 27. 6,500,000Files were tested 2.94%Family error rate! 0.358 % Error rate MtNet was trained (labeled data) MtNet, is a new deep learning malware classification architecture
  • 28. Tensorflow Vs. Torche Vs. Theano Marketing itself Tensorflow got the lead that would result in stronger community of users and faster development. Entities’ support Tensorflow has got Google, while Theano is still supported by University of Montreal. Torch supported by Facebook, twitter and NVIDIA! Visualizations Tensorflow has better computational graph visualizations but for Images and Graphs Theano is as good. Debugging Torch “automatic differentiation” is better for debugging than Theano and TensorFlow “symbolic computation”.
  • 29. Large-Scale Machine Learning How to train big model over big data?
  • 30. TensorFlowOnSpark ❏ Combines salient features from deep learning framework TensorFlow and big-data frameworks Apache Spark and Apache Hadoop ❏
  • 33. References ◎ Abadi, Martín, et al. "Tensorflow: Large-scale machine learning on heterogeneous distributed systems." arXiv preprint arXiv:1603.04467 (2016). ◎ Looks, Moshe, et al. "Deep learning with dynamic computation graphs." arXiv preprint arXiv:1702.02181 (2017). ◎ https://www.slideshare.net/MiguelFierro1/leveraging-deep-learning-applic ations-with-cntk ◎ https://www.slideshare.net/JeffreyShomaker/deep-learning-jeffshomaker12 017final ◎ PyTorch, Dynamic Computational Graphs and Modular Deep Learning - Carlos Perez ◎ https://github.com/Microsoft/CNTK ◎ https://medium.com/@ricardo.guerrero/deep-learning-frameworks-a-revi ew-before-finishing-2016-5b3ab4010b06 ◎ https://cs224d.stanford.edu/lectures/CS224d-Lecture7.pdf ◎ https://www.packtpub.com/books/content/getting-started-deep-learning ◎ https://leonardoaraujosantos.gitbooks.io/artificial-inteligence/content/tenso rflow.html ◎ https://github.com/yahoo/TensorFlowOnSpark ◎ http://www.dmtk.io/slides/distributedML-aaai2017.pdf