SlideShare ist ein Scribd-Unternehmen logo
1 von 25
Introduction to Deep Learning
July 12th 2017
Prepared for: Charlotte Bots & AI Meetup
Presenter: Abhishek Bhandwaldar
Data scientist at botsplash.com
They are all talking about AI especially
advancements in Deep Learning!
Photo credit: http://www.latercera.com/
AI Evolution
Credit: Nvidia.com at https://goo.gl/mY55TM
Artificial Intelligence Techniques
Cognitive Use Cases (Why DL?)
Computer Vision Self Driving Cars
Faces, Gaming
Medical / Sensors
Speech Processing Voice Recognition
Music Generation
Language Translation
Natural Language
Processing
CRM
Chatbots
ADs
Credit: kdnuggets.com
Deep Learning through Ages
1958
Perceptron
algorithm
Rosenblatt
created the
perceptron
algorithm
1965
Multilayer
perceptron
First algorithm for
multilayer
perceptron was
publisher by
Ivakhnenko
Image Recognition
Yan LeCun et al.
successfully applied
deep neural network
for image recognition
using convolution
1969 1998
Neural Network
Setbacks
Minsky and Papert
proved in their
published book
‘Perceptrons’ that it
has many limitation
Deep Learning Process
• Data Collection and Pre-processing
• Data division in train, dev and test sets
• Selection of Model architecture
• Training and performance benchmarking
• Tuning hyper-parameters and Repeat training
• Testing with Test set
Getting Started with Deep Learning
1. Python programming or alternative
2. GPU based Hardware
3. Deep Learning Frameworks
4. Basic knowledge of Neural Networks
5. Data sets (many available online)
Python Programming
Basic level skill. Learn from youtube.com or coursera.com
GPU Hardware and Training in Cloud
• CPU will work for simple workloads
Cloud Provider Pros Cons
Floydhub.com   Similar to heroku, Easy to
get started and use, Free
credits
No GUI. Difficult to get GPU
working for non Tensorflow
solutions.
Paperspace.com  Full blown desktop in cloud
with good GPU support.
UI lags and buggy but
usable.
Google ML Engine  Best for Tensorflow only
solution. Data labs is good
notebook environment.
No support beyond
Tensorflow
Amazon AWS   GPU supported systems Self hosting and
maintenance
Deep Learning Frameworks
• Keras is wrapper and makes it easy to work with DL frameworks!
Framework Sponsor Best for:
Tensorflow Google Popularity and ease of use
CNTK Microsoft Fast, Accurate and Growing
PyTorch Facebook Early adopter
MxNET Amazon Group of companies
Caffe, Theano Schools Researchers
Neural Networks Overview
• Linear and Non Linear Models
• Deep Neural Networks (Deep Learning name comes from here)
 Training
 Architecture
 Convolutional Neural Networks
 Recurrent Neural Networks
 Generative Adversial Neural Networks
Linear Models
• Output is linear function of input.
• The model is limited in learning
and addition of layers has no
effect.
• Computation on GPU is very
efficient.
Input
Linear
Function
Output
z = b + ∑ xiwi
Image source:
https://en.wikipedia.org/wiki/Generalized_linear_model
Non Linear Model and Relu
• By introducing non linearity model is able
to learn much better.
• The non linearity function most widely
used is Relu.
• f(x)=max(0,x)
• Other activations functions used :
• Sigmoid
• Tanh
• Relu is less computationally expensive.
Input
Linear
Function
Output
z = b + ∑ xiwi
Relu
output = max(0, z)
Image source: http://cs231n.github.io/neural-networks-
1/
Deep Neural Network & Architecture
• When we connect multiple neuron
together we have a fully connected
deep neural network.
• Making network deeper than wider.
• This helps in learning hierarchical
representation (Low level details to
high level concepts).
• Also decreases learnable
parameters.
Image source: http://cs231n.github.io/neural-networks-1/
Back Propagation and Neural Network Training
• Back propagation is the algorithm we use for neural network learning.
• The cost function widely used is the cross entropy cost function for calculating loss.
• Two Steps:
• Forward Pass: The data is passed through the network and the loss is calculated
• Backward Pass: Loss is propagated backwards by changing weights i.e. optimization
• Various methods for NN optimization:
• Stochastic Gradient Descent, Momentum, Nesterov accelerated gradient, RMSprop, Adagrad, Adam
Demo
Feed Forward Neural Network
at Tensorflow Playground
Convolutional neural network
Has 3 Types of Layers.
• Convolution Layer: A convolutional layer applies convolution to input
• Pooling Layer/Subsampling: This layer combines all output into single value.
• Fully-connected layer: Simple fully connected network
Image source: LeCun, Yann; Léon Bottou; Yoshua Bengio; Patrick Haffner (1998). "Gradient-based learning applied to document recognition" (PDF).
Proceedings of the IEEE.
CNN Example
LeNet-5, convolutional neural
networks
source:http://yann.lecun.com/exdb/lenet/
Code
Walkthrough
Handwriting Recognition on
MNIST data set
Recurrent Neural Network
• This type of Neural network is used for sequence data. Ideal for text data.
• The output of hidden layer is fed back into itself (feedback).
• RNN are Turing-complete. But practically they are very difficult to implement
because of the gradient explosion/vanishing problem.
• To tackle this issue we have the LSTM network.
Image source: http://karpathy.github.io/2015/05/21/rnn-
effectiveness/
Generative Adversarial Networks
• According to Yan LeCun GAN were the next big thing.
• Architecture is Simple: We have Discriminative model has task of
determining whether image is image looks natural or not.
• The task of generator is to generate image in order to fool discriminator.
Tips for training Deep Neural Network
• Batch Learning:
• Pass over complete training examples is made and then weights are updated.
• In Mini-batch pass over small batch is made and weights are updated after every batch
• Fast and parallel training can be implemented on GPU. Widely used.
• Online Learning:
• After completing pass over every example weights are updated. Easy to train on new examples
• Very slow.
• Convolutions can be implemented parallelly and gain speed up on GPU.
• In RNN, multiple examples can be processed parallelly if using batch learning.
• Using techniques like dropout and regularization to prevent overfitting.
• Gathering more examples to prevent overfitting and generalize better.
• Increase number of layer to prevent underfitting.
Resources
Neural Network:
• Neural Networks for Machine Learning | Coursera
• Neural Networks by Hugo Larochelle
• Neural Networks, Manifolds, and Topology -- colah's blog
• Distill — Latest articles about machine learning
• Deep Learning Book
• An overview of gradient descent optimization algorithms
• Deep Learning By Google
• SIRAJ RAVAL'S DEEP LEARNING (Also available on Siraj Rawal’s YouTube channel)
• Neural Networks and Deep Learning
• Understanding Activation Functions in Neural Networks
RNN:
• The Unreasonable Effectiveness of Recurrent Neural Networks
• Recurrent Neural Networks Tutorial
• How to build a Recurrent Neural Network in TensorFlow
CNN:
• Convolutional Neural Network - Deep Learning
• Convolutional Neural Networks (LeNet)
Questions & Feedback

Weitere ähnliche Inhalte

Was ist angesagt?

Deep Learning - A Literature survey
Deep Learning - A Literature surveyDeep Learning - A Literature survey
Deep Learning - A Literature surveyAkshay Hegde
 
Geek Night 17.0 - Artificial Intelligence and Machine Learning
Geek Night 17.0 - Artificial Intelligence and Machine LearningGeek Night 17.0 - Artificial Intelligence and Machine Learning
Geek Night 17.0 - Artificial Intelligence and Machine LearningGeekNightHyderabad
 
Deep learning - Conceptual understanding and applications
Deep learning - Conceptual understanding and applicationsDeep learning - Conceptual understanding and applications
Deep learning - Conceptual understanding and applicationsBuhwan Jeong
 
Convolutional Neural Network for Alzheimer’s disease diagnosis with Neuroim...
Convolutional Neural Network for Alzheimer’s disease diagnosis with Neuroim...Convolutional Neural Network for Alzheimer’s disease diagnosis with Neuroim...
Convolutional Neural Network for Alzheimer’s disease diagnosis with Neuroim...Seonho Park
 
Details of Lazy Deep Learning for Images Recognition in ZZ Photo app
Details of Lazy Deep Learning for Images Recognition in ZZ Photo appDetails of Lazy Deep Learning for Images Recognition in ZZ Photo app
Details of Lazy Deep Learning for Images Recognition in ZZ Photo appPAY2 YOU
 
HML: Historical View and Trends of Deep Learning
HML: Historical View and Trends of Deep LearningHML: Historical View and Trends of Deep Learning
HML: Historical View and Trends of Deep LearningYan Xu
 
Introduction to deep learning
Introduction to deep learningIntroduction to deep learning
Introduction to deep learningdoppenhe
 
Language translation with Deep Learning (RNN) with TensorFlow
Language translation with Deep Learning (RNN) with TensorFlowLanguage translation with Deep Learning (RNN) with TensorFlow
Language translation with Deep Learning (RNN) with TensorFlowS N
 
Deep Learning for Robotics
Deep Learning for RoboticsDeep Learning for Robotics
Deep Learning for RoboticsIntel Nervana
 
MDEC Data Matters Series: machine learning and Deep Learning, A Primer
MDEC Data Matters Series: machine learning and Deep Learning, A PrimerMDEC Data Matters Series: machine learning and Deep Learning, A Primer
MDEC Data Matters Series: machine learning and Deep Learning, A PrimerPoo Kuan Hoong
 
Deep learning - A Visual Introduction
Deep learning - A Visual IntroductionDeep learning - A Visual Introduction
Deep learning - A Visual IntroductionLukas Masuch
 
AI&BigData Lab. Артем Чернодуб "Распознавание изображений методом Lazy Deep ...
AI&BigData Lab. Артем Чернодуб  "Распознавание изображений методом Lazy Deep ...AI&BigData Lab. Артем Чернодуб  "Распознавание изображений методом Lazy Deep ...
AI&BigData Lab. Артем Чернодуб "Распознавание изображений методом Lazy Deep ...GeeksLab Odessa
 
101: Convolutional Neural Networks
101: Convolutional Neural Networks 101: Convolutional Neural Networks
101: Convolutional Neural Networks Mad Scientists
 
Handwritten Recognition using Deep Learning with R
Handwritten Recognition using Deep Learning with RHandwritten Recognition using Deep Learning with R
Handwritten Recognition using Deep Learning with RPoo Kuan Hoong
 
Deep Learning: a birds eye view
Deep Learning: a birds eye viewDeep Learning: a birds eye view
Deep Learning: a birds eye viewRoelof Pieters
 
Deep learning intro
Deep learning introDeep learning intro
Deep learning introbeamandrew
 
From Conventional Machine Learning to Deep Learning and Beyond.pptx
From Conventional Machine Learning to Deep Learning and Beyond.pptxFrom Conventional Machine Learning to Deep Learning and Beyond.pptx
From Conventional Machine Learning to Deep Learning and Beyond.pptxChun-Hao Chang
 
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 TeterwakPyData
 
Building distributed deep learning engine
Building distributed deep learning engineBuilding distributed deep learning engine
Building distributed deep learning engineGuangdeng Liao
 

Was ist angesagt? (20)

Deep Learning - A Literature survey
Deep Learning - A Literature surveyDeep Learning - A Literature survey
Deep Learning - A Literature survey
 
Geek Night 17.0 - Artificial Intelligence and Machine Learning
Geek Night 17.0 - Artificial Intelligence and Machine LearningGeek Night 17.0 - Artificial Intelligence and Machine Learning
Geek Night 17.0 - Artificial Intelligence and Machine Learning
 
Deep learning - Conceptual understanding and applications
Deep learning - Conceptual understanding and applicationsDeep learning - Conceptual understanding and applications
Deep learning - Conceptual understanding and applications
 
Convolutional Neural Network for Alzheimer’s disease diagnosis with Neuroim...
Convolutional Neural Network for Alzheimer’s disease diagnosis with Neuroim...Convolutional Neural Network for Alzheimer’s disease diagnosis with Neuroim...
Convolutional Neural Network for Alzheimer’s disease diagnosis with Neuroim...
 
Details of Lazy Deep Learning for Images Recognition in ZZ Photo app
Details of Lazy Deep Learning for Images Recognition in ZZ Photo appDetails of Lazy Deep Learning for Images Recognition in ZZ Photo app
Details of Lazy Deep Learning for Images Recognition in ZZ Photo app
 
HML: Historical View and Trends of Deep Learning
HML: Historical View and Trends of Deep LearningHML: Historical View and Trends of Deep Learning
HML: Historical View and Trends of Deep Learning
 
Introduction to deep learning
Introduction to deep learningIntroduction to deep learning
Introduction to deep learning
 
Language translation with Deep Learning (RNN) with TensorFlow
Language translation with Deep Learning (RNN) with TensorFlowLanguage translation with Deep Learning (RNN) with TensorFlow
Language translation with Deep Learning (RNN) with TensorFlow
 
Deep Learning for Robotics
Deep Learning for RoboticsDeep Learning for Robotics
Deep Learning for Robotics
 
MDEC Data Matters Series: machine learning and Deep Learning, A Primer
MDEC Data Matters Series: machine learning and Deep Learning, A PrimerMDEC Data Matters Series: machine learning and Deep Learning, A Primer
MDEC Data Matters Series: machine learning and Deep Learning, A Primer
 
Introduction to Deep learning
Introduction to Deep learningIntroduction to Deep learning
Introduction to Deep learning
 
Deep learning - A Visual Introduction
Deep learning - A Visual IntroductionDeep learning - A Visual Introduction
Deep learning - A Visual Introduction
 
AI&BigData Lab. Артем Чернодуб "Распознавание изображений методом Lazy Deep ...
AI&BigData Lab. Артем Чернодуб  "Распознавание изображений методом Lazy Deep ...AI&BigData Lab. Артем Чернодуб  "Распознавание изображений методом Lazy Deep ...
AI&BigData Lab. Артем Чернодуб "Распознавание изображений методом Lazy Deep ...
 
101: Convolutional Neural Networks
101: Convolutional Neural Networks 101: Convolutional Neural Networks
101: Convolutional Neural Networks
 
Handwritten Recognition using Deep Learning with R
Handwritten Recognition using Deep Learning with RHandwritten Recognition using Deep Learning with R
Handwritten Recognition using Deep Learning with R
 
Deep Learning: a birds eye view
Deep Learning: a birds eye viewDeep Learning: a birds eye view
Deep Learning: a birds eye view
 
Deep learning intro
Deep learning introDeep learning intro
Deep learning intro
 
From Conventional Machine Learning to Deep Learning and Beyond.pptx
From Conventional Machine Learning to Deep Learning and Beyond.pptxFrom Conventional Machine Learning to Deep Learning and Beyond.pptx
From Conventional Machine Learning to Deep Learning and Beyond.pptx
 
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
 
Building distributed deep learning engine
Building distributed deep learning engineBuilding distributed deep learning engine
Building distributed deep learning engine
 

Ähnlich wie Introduction to deep learning

AI powered emotion recognition: From Inception to Production - Global AI Conf...
AI powered emotion recognition: From Inception to Production - Global AI Conf...AI powered emotion recognition: From Inception to Production - Global AI Conf...
AI powered emotion recognition: From Inception to Production - Global AI Conf...Vandana Kannan
 
AI powered emotion recognition: From Inception to Production - Global AI Conf...
AI powered emotion recognition: From Inception to Production - Global AI Conf...AI powered emotion recognition: From Inception to Production - Global AI Conf...
AI powered emotion recognition: From Inception to Production - Global AI Conf...Apache MXNet
 
Big Data Malaysia - A Primer on Deep Learning
Big Data Malaysia - A Primer on Deep LearningBig Data Malaysia - A Primer on Deep Learning
Big Data Malaysia - A Primer on Deep LearningPoo Kuan Hoong
 
DSRLab seminar Introduction to deep learning
DSRLab seminar   Introduction to deep learningDSRLab seminar   Introduction to deep learning
DSRLab seminar Introduction to deep learningPoo Kuan Hoong
 
Introduction to deep learning
Introduction to deep learningIntroduction to deep learning
Introduction to deep learningAmr Rashed
 
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 101Felipe Prado
 
Dp2 ppt by_bikramjit_chowdhury_final
Dp2 ppt by_bikramjit_chowdhury_finalDp2 ppt by_bikramjit_chowdhury_final
Dp2 ppt by_bikramjit_chowdhury_finalBikramjit Chowdhury
 
Deep Learning: Evolution of ML from Statistical to Brain-like Computing- Data...
Deep Learning: Evolution of ML from Statistical to Brain-like Computing- Data...Deep Learning: Evolution of ML from Statistical to Brain-like Computing- Data...
Deep Learning: Evolution of ML from Statistical to Brain-like Computing- Data...Impetus Technologies
 
Introduction to deep learning
Introduction to deep learningIntroduction to deep learning
Introduction to deep learningVishwas Lele
 
Machine Duping 101: Pwning Deep Learning Systems
Machine Duping 101: Pwning Deep Learning SystemsMachine Duping 101: Pwning Deep Learning Systems
Machine Duping 101: Pwning Deep Learning SystemsClarence Chio
 
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 FaceTakrim Ul Islam Laskar
 
DLD meetup 2017, Efficient Deep Learning
DLD meetup 2017, Efficient Deep LearningDLD meetup 2017, Efficient Deep Learning
DLD meetup 2017, Efficient Deep LearningBrodmann17
 
Introduction of Machine learning and Deep Learning
Introduction of Machine learning and Deep LearningIntroduction of Machine learning and Deep Learning
Introduction of Machine learning and Deep LearningMadhu Sanjeevi (Mady)
 
Startup.Ml: Using neon for NLP and Localization Applications
Startup.Ml: Using neon for NLP and Localization Applications Startup.Ml: Using neon for NLP and Localization Applications
Startup.Ml: Using neon for NLP and Localization Applications Intel Nervana
 
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 FarooquiDatabricks
 
Introduction to Recurrent Neural Network
Introduction to Recurrent Neural NetworkIntroduction to Recurrent Neural Network
Introduction to Recurrent Neural NetworkYan Xu
 

Ähnlich wie Introduction to deep learning (20)

AI powered emotion recognition: From Inception to Production - Global AI Conf...
AI powered emotion recognition: From Inception to Production - Global AI Conf...AI powered emotion recognition: From Inception to Production - Global AI Conf...
AI powered emotion recognition: From Inception to Production - Global AI Conf...
 
AI powered emotion recognition: From Inception to Production - Global AI Conf...
AI powered emotion recognition: From Inception to Production - Global AI Conf...AI powered emotion recognition: From Inception to Production - Global AI Conf...
AI powered emotion recognition: From Inception to Production - Global AI Conf...
 
Big Data Malaysia - A Primer on Deep Learning
Big Data Malaysia - A Primer on Deep LearningBig Data Malaysia - A Primer on Deep Learning
Big Data Malaysia - A Primer on Deep Learning
 
DSRLab seminar Introduction to deep learning
DSRLab seminar   Introduction to deep learningDSRLab seminar   Introduction to deep learning
DSRLab seminar Introduction to deep learning
 
Introduction to deep learning
Introduction to deep learningIntroduction to deep learning
Introduction to deep learning
 
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
 
Dp2 ppt by_bikramjit_chowdhury_final
Dp2 ppt by_bikramjit_chowdhury_finalDp2 ppt by_bikramjit_chowdhury_final
Dp2 ppt by_bikramjit_chowdhury_final
 
Deep Learning: Evolution of ML from Statistical to Brain-like Computing- Data...
Deep Learning: Evolution of ML from Statistical to Brain-like Computing- Data...Deep Learning: Evolution of ML from Statistical to Brain-like Computing- Data...
Deep Learning: Evolution of ML from Statistical to Brain-like Computing- Data...
 
Deep learning
Deep learningDeep learning
Deep learning
 
ppt.pdf
ppt.pdfppt.pdf
ppt.pdf
 
Computer Design Concepts for Machine Learning
Computer Design Concepts for Machine LearningComputer Design Concepts for Machine Learning
Computer Design Concepts for Machine Learning
 
Introduction to deep learning
Introduction to deep learningIntroduction to deep learning
Introduction to deep learning
 
Development of Deep Learning Architecture
Development of Deep Learning ArchitectureDevelopment of Deep Learning Architecture
Development of Deep Learning Architecture
 
Machine Duping 101: Pwning Deep Learning Systems
Machine Duping 101: Pwning Deep Learning SystemsMachine Duping 101: Pwning Deep Learning Systems
Machine Duping 101: Pwning Deep Learning Systems
 
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
 
DLD meetup 2017, Efficient Deep Learning
DLD meetup 2017, Efficient Deep LearningDLD meetup 2017, Efficient Deep Learning
DLD meetup 2017, Efficient Deep Learning
 
Introduction of Machine learning and Deep Learning
Introduction of Machine learning and Deep LearningIntroduction of Machine learning and Deep Learning
Introduction of Machine learning and Deep Learning
 
Startup.Ml: Using neon for NLP and Localization Applications
Startup.Ml: Using neon for NLP and Localization Applications Startup.Ml: Using neon for NLP and Localization Applications
Startup.Ml: Using neon for NLP and Localization Applications
 
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
 
Introduction to Recurrent Neural Network
Introduction to Recurrent Neural NetworkIntroduction to Recurrent Neural Network
Introduction to Recurrent Neural Network
 

Kürzlich hochgeladen

Edukaciniai dropshipping via API with DroFx
Edukaciniai dropshipping via API with DroFxEdukaciniai dropshipping via API with DroFx
Edukaciniai dropshipping via API with DroFxolyaivanovalion
 
Data-Analysis for Chicago Crime Data 2023
Data-Analysis for Chicago Crime Data  2023Data-Analysis for Chicago Crime Data  2023
Data-Analysis for Chicago Crime Data 2023ymrp368
 
100-Concepts-of-AI by Anupama Kate .pptx
100-Concepts-of-AI by Anupama Kate .pptx100-Concepts-of-AI by Anupama Kate .pptx
100-Concepts-of-AI by Anupama Kate .pptxAnupama Kate
 
Invezz.com - Grow your wealth with trading signals
Invezz.com - Grow your wealth with trading signalsInvezz.com - Grow your wealth with trading signals
Invezz.com - Grow your wealth with trading signalsInvezz1
 
Cheap Rate Call girls Sarita Vihar Delhi 9205541914 shot 1500 night
Cheap Rate Call girls Sarita Vihar Delhi 9205541914 shot 1500 nightCheap Rate Call girls Sarita Vihar Delhi 9205541914 shot 1500 night
Cheap Rate Call girls Sarita Vihar Delhi 9205541914 shot 1500 nightDelhi Call girls
 
Best VIP Call Girls Noida Sector 39 Call Me: 8448380779
Best VIP Call Girls Noida Sector 39 Call Me: 8448380779Best VIP Call Girls Noida Sector 39 Call Me: 8448380779
Best VIP Call Girls Noida Sector 39 Call Me: 8448380779Delhi Call girls
 
BigBuy dropshipping via API with DroFx.pptx
BigBuy dropshipping via API with DroFx.pptxBigBuy dropshipping via API with DroFx.pptx
BigBuy dropshipping via API with DroFx.pptxolyaivanovalion
 
Midocean dropshipping via API with DroFx
Midocean dropshipping via API with DroFxMidocean dropshipping via API with DroFx
Midocean dropshipping via API with DroFxolyaivanovalion
 
Call Girls 🫤 Dwarka ➡️ 9711199171 ➡️ Delhi 🫦 Two shot with one girl
Call Girls 🫤 Dwarka ➡️ 9711199171 ➡️ Delhi 🫦 Two shot with one girlCall Girls 🫤 Dwarka ➡️ 9711199171 ➡️ Delhi 🫦 Two shot with one girl
Call Girls 🫤 Dwarka ➡️ 9711199171 ➡️ Delhi 🫦 Two shot with one girlkumarajju5765
 
Vip Model Call Girls (Delhi) Karol Bagh 9711199171✔️Body to body massage wit...
Vip Model  Call Girls (Delhi) Karol Bagh 9711199171✔️Body to body massage wit...Vip Model  Call Girls (Delhi) Karol Bagh 9711199171✔️Body to body massage wit...
Vip Model Call Girls (Delhi) Karol Bagh 9711199171✔️Body to body massage wit...shivangimorya083
 
Mature dropshipping via API with DroFx.pptx
Mature dropshipping via API with DroFx.pptxMature dropshipping via API with DroFx.pptx
Mature dropshipping via API with DroFx.pptxolyaivanovalion
 
Call me @ 9892124323 Cheap Rate Call Girls in Vashi with Real Photo 100% Secure
Call me @ 9892124323  Cheap Rate Call Girls in Vashi with Real Photo 100% SecureCall me @ 9892124323  Cheap Rate Call Girls in Vashi with Real Photo 100% Secure
Call me @ 9892124323 Cheap Rate Call Girls in Vashi with Real Photo 100% SecurePooja Nehwal
 
Market Analysis in the 5 Largest Economic Countries in Southeast Asia.pdf
Market Analysis in the 5 Largest Economic Countries in Southeast Asia.pdfMarket Analysis in the 5 Largest Economic Countries in Southeast Asia.pdf
Market Analysis in the 5 Largest Economic Countries in Southeast Asia.pdfRachmat Ramadhan H
 
Halmar dropshipping via API with DroFx
Halmar  dropshipping  via API with DroFxHalmar  dropshipping  via API with DroFx
Halmar dropshipping via API with DroFxolyaivanovalion
 
Delhi Call Girls CP 9711199171 ☎✔👌✔ Whatsapp Hard And Sexy Vip Call
Delhi Call Girls CP 9711199171 ☎✔👌✔ Whatsapp Hard And Sexy Vip CallDelhi Call Girls CP 9711199171 ☎✔👌✔ Whatsapp Hard And Sexy Vip Call
Delhi Call Girls CP 9711199171 ☎✔👌✔ Whatsapp Hard And Sexy Vip Callshivangimorya083
 
BPAC WITH UFSBI GENERAL PRESENTATION 18_05_2017-1.pptx
BPAC WITH UFSBI GENERAL PRESENTATION 18_05_2017-1.pptxBPAC WITH UFSBI GENERAL PRESENTATION 18_05_2017-1.pptx
BPAC WITH UFSBI GENERAL PRESENTATION 18_05_2017-1.pptxMohammedJunaid861692
 
Generative AI on Enterprise Cloud with NiFi and Milvus
Generative AI on Enterprise Cloud with NiFi and MilvusGenerative AI on Enterprise Cloud with NiFi and Milvus
Generative AI on Enterprise Cloud with NiFi and MilvusTimothy Spann
 
꧁❤ Greater Noida Call Girls Delhi ❤꧂ 9711199171 ☎️ Hard And Sexy Vip Call
꧁❤ Greater Noida Call Girls Delhi ❤꧂ 9711199171 ☎️ Hard And Sexy Vip Call꧁❤ Greater Noida Call Girls Delhi ❤꧂ 9711199171 ☎️ Hard And Sexy Vip Call
꧁❤ Greater Noida Call Girls Delhi ❤꧂ 9711199171 ☎️ Hard And Sexy Vip Callshivangimorya083
 

Kürzlich hochgeladen (20)

Edukaciniai dropshipping via API with DroFx
Edukaciniai dropshipping via API with DroFxEdukaciniai dropshipping via API with DroFx
Edukaciniai dropshipping via API with DroFx
 
Data-Analysis for Chicago Crime Data 2023
Data-Analysis for Chicago Crime Data  2023Data-Analysis for Chicago Crime Data  2023
Data-Analysis for Chicago Crime Data 2023
 
100-Concepts-of-AI by Anupama Kate .pptx
100-Concepts-of-AI by Anupama Kate .pptx100-Concepts-of-AI by Anupama Kate .pptx
100-Concepts-of-AI by Anupama Kate .pptx
 
Invezz.com - Grow your wealth with trading signals
Invezz.com - Grow your wealth with trading signalsInvezz.com - Grow your wealth with trading signals
Invezz.com - Grow your wealth with trading signals
 
Cheap Rate Call girls Sarita Vihar Delhi 9205541914 shot 1500 night
Cheap Rate Call girls Sarita Vihar Delhi 9205541914 shot 1500 nightCheap Rate Call girls Sarita Vihar Delhi 9205541914 shot 1500 night
Cheap Rate Call girls Sarita Vihar Delhi 9205541914 shot 1500 night
 
Best VIP Call Girls Noida Sector 39 Call Me: 8448380779
Best VIP Call Girls Noida Sector 39 Call Me: 8448380779Best VIP Call Girls Noida Sector 39 Call Me: 8448380779
Best VIP Call Girls Noida Sector 39 Call Me: 8448380779
 
BigBuy dropshipping via API with DroFx.pptx
BigBuy dropshipping via API with DroFx.pptxBigBuy dropshipping via API with DroFx.pptx
BigBuy dropshipping via API with DroFx.pptx
 
Midocean dropshipping via API with DroFx
Midocean dropshipping via API with DroFxMidocean dropshipping via API with DroFx
Midocean dropshipping via API with DroFx
 
Call Girls 🫤 Dwarka ➡️ 9711199171 ➡️ Delhi 🫦 Two shot with one girl
Call Girls 🫤 Dwarka ➡️ 9711199171 ➡️ Delhi 🫦 Two shot with one girlCall Girls 🫤 Dwarka ➡️ 9711199171 ➡️ Delhi 🫦 Two shot with one girl
Call Girls 🫤 Dwarka ➡️ 9711199171 ➡️ Delhi 🫦 Two shot with one girl
 
Vip Model Call Girls (Delhi) Karol Bagh 9711199171✔️Body to body massage wit...
Vip Model  Call Girls (Delhi) Karol Bagh 9711199171✔️Body to body massage wit...Vip Model  Call Girls (Delhi) Karol Bagh 9711199171✔️Body to body massage wit...
Vip Model Call Girls (Delhi) Karol Bagh 9711199171✔️Body to body massage wit...
 
Mature dropshipping via API with DroFx.pptx
Mature dropshipping via API with DroFx.pptxMature dropshipping via API with DroFx.pptx
Mature dropshipping via API with DroFx.pptx
 
Call me @ 9892124323 Cheap Rate Call Girls in Vashi with Real Photo 100% Secure
Call me @ 9892124323  Cheap Rate Call Girls in Vashi with Real Photo 100% SecureCall me @ 9892124323  Cheap Rate Call Girls in Vashi with Real Photo 100% Secure
Call me @ 9892124323 Cheap Rate Call Girls in Vashi with Real Photo 100% Secure
 
Market Analysis in the 5 Largest Economic Countries in Southeast Asia.pdf
Market Analysis in the 5 Largest Economic Countries in Southeast Asia.pdfMarket Analysis in the 5 Largest Economic Countries in Southeast Asia.pdf
Market Analysis in the 5 Largest Economic Countries in Southeast Asia.pdf
 
Halmar dropshipping via API with DroFx
Halmar  dropshipping  via API with DroFxHalmar  dropshipping  via API with DroFx
Halmar dropshipping via API with DroFx
 
Abortion pills in Doha Qatar (+966572737505 ! Get Cytotec
Abortion pills in Doha Qatar (+966572737505 ! Get CytotecAbortion pills in Doha Qatar (+966572737505 ! Get Cytotec
Abortion pills in Doha Qatar (+966572737505 ! Get Cytotec
 
Delhi Call Girls CP 9711199171 ☎✔👌✔ Whatsapp Hard And Sexy Vip Call
Delhi Call Girls CP 9711199171 ☎✔👌✔ Whatsapp Hard And Sexy Vip CallDelhi Call Girls CP 9711199171 ☎✔👌✔ Whatsapp Hard And Sexy Vip Call
Delhi Call Girls CP 9711199171 ☎✔👌✔ Whatsapp Hard And Sexy Vip Call
 
BPAC WITH UFSBI GENERAL PRESENTATION 18_05_2017-1.pptx
BPAC WITH UFSBI GENERAL PRESENTATION 18_05_2017-1.pptxBPAC WITH UFSBI GENERAL PRESENTATION 18_05_2017-1.pptx
BPAC WITH UFSBI GENERAL PRESENTATION 18_05_2017-1.pptx
 
Generative AI on Enterprise Cloud with NiFi and Milvus
Generative AI on Enterprise Cloud with NiFi and MilvusGenerative AI on Enterprise Cloud with NiFi and Milvus
Generative AI on Enterprise Cloud with NiFi and Milvus
 
꧁❤ Greater Noida Call Girls Delhi ❤꧂ 9711199171 ☎️ Hard And Sexy Vip Call
꧁❤ Greater Noida Call Girls Delhi ❤꧂ 9711199171 ☎️ Hard And Sexy Vip Call꧁❤ Greater Noida Call Girls Delhi ❤꧂ 9711199171 ☎️ Hard And Sexy Vip Call
꧁❤ Greater Noida Call Girls Delhi ❤꧂ 9711199171 ☎️ Hard And Sexy Vip Call
 
Delhi 99530 vip 56974 Genuine Escort Service Call Girls in Kishangarh
Delhi 99530 vip 56974 Genuine Escort Service Call Girls in  KishangarhDelhi 99530 vip 56974 Genuine Escort Service Call Girls in  Kishangarh
Delhi 99530 vip 56974 Genuine Escort Service Call Girls in Kishangarh
 

Introduction to deep learning

  • 1. Introduction to Deep Learning July 12th 2017 Prepared for: Charlotte Bots & AI Meetup Presenter: Abhishek Bhandwaldar Data scientist at botsplash.com
  • 2. They are all talking about AI especially advancements in Deep Learning! Photo credit: http://www.latercera.com/
  • 3. AI Evolution Credit: Nvidia.com at https://goo.gl/mY55TM
  • 5. Cognitive Use Cases (Why DL?) Computer Vision Self Driving Cars Faces, Gaming Medical / Sensors Speech Processing Voice Recognition Music Generation Language Translation Natural Language Processing CRM Chatbots ADs Credit: kdnuggets.com
  • 6. Deep Learning through Ages 1958 Perceptron algorithm Rosenblatt created the perceptron algorithm 1965 Multilayer perceptron First algorithm for multilayer perceptron was publisher by Ivakhnenko Image Recognition Yan LeCun et al. successfully applied deep neural network for image recognition using convolution 1969 1998 Neural Network Setbacks Minsky and Papert proved in their published book ‘Perceptrons’ that it has many limitation
  • 7. Deep Learning Process • Data Collection and Pre-processing • Data division in train, dev and test sets • Selection of Model architecture • Training and performance benchmarking • Tuning hyper-parameters and Repeat training • Testing with Test set
  • 8. Getting Started with Deep Learning 1. Python programming or alternative 2. GPU based Hardware 3. Deep Learning Frameworks 4. Basic knowledge of Neural Networks 5. Data sets (many available online)
  • 9. Python Programming Basic level skill. Learn from youtube.com or coursera.com
  • 10. GPU Hardware and Training in Cloud • CPU will work for simple workloads Cloud Provider Pros Cons Floydhub.com   Similar to heroku, Easy to get started and use, Free credits No GUI. Difficult to get GPU working for non Tensorflow solutions. Paperspace.com  Full blown desktop in cloud with good GPU support. UI lags and buggy but usable. Google ML Engine  Best for Tensorflow only solution. Data labs is good notebook environment. No support beyond Tensorflow Amazon AWS   GPU supported systems Self hosting and maintenance
  • 11. Deep Learning Frameworks • Keras is wrapper and makes it easy to work with DL frameworks! Framework Sponsor Best for: Tensorflow Google Popularity and ease of use CNTK Microsoft Fast, Accurate and Growing PyTorch Facebook Early adopter MxNET Amazon Group of companies Caffe, Theano Schools Researchers
  • 12. Neural Networks Overview • Linear and Non Linear Models • Deep Neural Networks (Deep Learning name comes from here)  Training  Architecture  Convolutional Neural Networks  Recurrent Neural Networks  Generative Adversial Neural Networks
  • 13. Linear Models • Output is linear function of input. • The model is limited in learning and addition of layers has no effect. • Computation on GPU is very efficient. Input Linear Function Output z = b + ∑ xiwi Image source: https://en.wikipedia.org/wiki/Generalized_linear_model
  • 14. Non Linear Model and Relu • By introducing non linearity model is able to learn much better. • The non linearity function most widely used is Relu. • f(x)=max(0,x) • Other activations functions used : • Sigmoid • Tanh • Relu is less computationally expensive. Input Linear Function Output z = b + ∑ xiwi Relu output = max(0, z) Image source: http://cs231n.github.io/neural-networks- 1/
  • 15. Deep Neural Network & Architecture • When we connect multiple neuron together we have a fully connected deep neural network. • Making network deeper than wider. • This helps in learning hierarchical representation (Low level details to high level concepts). • Also decreases learnable parameters. Image source: http://cs231n.github.io/neural-networks-1/
  • 16. Back Propagation and Neural Network Training • Back propagation is the algorithm we use for neural network learning. • The cost function widely used is the cross entropy cost function for calculating loss. • Two Steps: • Forward Pass: The data is passed through the network and the loss is calculated • Backward Pass: Loss is propagated backwards by changing weights i.e. optimization • Various methods for NN optimization: • Stochastic Gradient Descent, Momentum, Nesterov accelerated gradient, RMSprop, Adagrad, Adam
  • 17. Demo Feed Forward Neural Network at Tensorflow Playground
  • 18. Convolutional neural network Has 3 Types of Layers. • Convolution Layer: A convolutional layer applies convolution to input • Pooling Layer/Subsampling: This layer combines all output into single value. • Fully-connected layer: Simple fully connected network Image source: LeCun, Yann; Léon Bottou; Yoshua Bengio; Patrick Haffner (1998). "Gradient-based learning applied to document recognition" (PDF). Proceedings of the IEEE.
  • 19. CNN Example LeNet-5, convolutional neural networks source:http://yann.lecun.com/exdb/lenet/
  • 21. Recurrent Neural Network • This type of Neural network is used for sequence data. Ideal for text data. • The output of hidden layer is fed back into itself (feedback). • RNN are Turing-complete. But practically they are very difficult to implement because of the gradient explosion/vanishing problem. • To tackle this issue we have the LSTM network. Image source: http://karpathy.github.io/2015/05/21/rnn- effectiveness/
  • 22. Generative Adversarial Networks • According to Yan LeCun GAN were the next big thing. • Architecture is Simple: We have Discriminative model has task of determining whether image is image looks natural or not. • The task of generator is to generate image in order to fool discriminator.
  • 23. Tips for training Deep Neural Network • Batch Learning: • Pass over complete training examples is made and then weights are updated. • In Mini-batch pass over small batch is made and weights are updated after every batch • Fast and parallel training can be implemented on GPU. Widely used. • Online Learning: • After completing pass over every example weights are updated. Easy to train on new examples • Very slow. • Convolutions can be implemented parallelly and gain speed up on GPU. • In RNN, multiple examples can be processed parallelly if using batch learning. • Using techniques like dropout and regularization to prevent overfitting. • Gathering more examples to prevent overfitting and generalize better. • Increase number of layer to prevent underfitting.
  • 24. Resources Neural Network: • Neural Networks for Machine Learning | Coursera • Neural Networks by Hugo Larochelle • Neural Networks, Manifolds, and Topology -- colah's blog • Distill — Latest articles about machine learning • Deep Learning Book • An overview of gradient descent optimization algorithms • Deep Learning By Google • SIRAJ RAVAL'S DEEP LEARNING (Also available on Siraj Rawal’s YouTube channel) • Neural Networks and Deep Learning • Understanding Activation Functions in Neural Networks RNN: • The Unreasonable Effectiveness of Recurrent Neural Networks • Recurrent Neural Networks Tutorial • How to build a Recurrent Neural Network in TensorFlow CNN: • Convolutional Neural Network - Deep Learning • Convolutional Neural Networks (LeNet)

Hinweis der Redaktion

  1. It is very hard for us to build a program that can do 3-D object recognition from novel viewpoint with new lighting and changing setting. This process happens in our brain but it is hard for us to build a program that can do this as we don’t know how our brain does it. Even if we get good idea of how the brain does the program we build will be very complicated. It is also hard to write a program that computes probability that a credit card transaction is fraudulent. There might not be any simple rules. The final program might be an collection of many weak rules. Fraud is moving target, program needs to keep updating itself. The Machine learning approach takes large number of examples that specify a particular task. It produces a program that can do that job for us. If we train it properly it will work on new cases as well i.e. it generalizes properly. The program will look nothing like the one we usually write. It will have lot of numbers. If the data changes the program can change too by training. Massive amount of computations are now cheaper and hence it is easy to train a program rather than paying someone to build one. Some of examples best solved by machine learning: Pattern Recognition, Anomaly detection, Prediction
  2. In 1958 Rosenblatt created the perceptron algorithm. He made many tall claims. The first algorithm for multilayer perceptron was publisher by Ivakhnenko in 1965. In 1969, Minsky and Papert proved in their published book ‘Perceptrons’ that it has many limitation. This brought depression in neural network research. In their research they proved that a single layer perceptron was unable to learn ex-or function and current computers where not capable of multilayer network. In 1998 Yan LeCun et al. successfully applied deep neural network for image recognition using convolution.
  3. Linear functions are limited. We want to be able to learn anything possible. So we need a way to compute not non linearity. We had online linear units, stacking of multiple layers, it will still behave like a single layer network as summing this layer gives a linear function. This is not strong enough to model complex data. We also want it to be differentiable. That is we want to be able to calculate derivative
  4. We introduce non linearity by doing minimal amount of work. Other types of function used are Sigmoid function, Tanh function a scaled form of sigmoid function The sigmoid function was popular and was used in most of machine learning models. But sigmoid and tanh suffers from problem of gradient vanishing i.e. when input is very small or very large the gradients are very small. At this point the gradient is close to 0 and hence weight updates are negligible. Hence learning can get very slow or even stop and Neural network takes time to converge. To counter this we use Relu unit. This unit is Non linear. We insert Relu unit. So our input first passes through linear unit where it is multiplied by the weight matrix and bias is added. The output then goes through Relu unit. The Relu function is 0 for all input less than 0 and x if for input x > 0 Relu at this point proves to be much better than sigmoid and Tanh. But relu has problem when input is negative or 0. At this time gradient is 0 and network learns slowly. This is called Dying relu problem To tackle this we have leaky relu where at negative input output is very small but not 0.
  5. A typical neural network looks like bunch of neurons stacked on each other. The input of the network is often vectorized. The hidden layer of made up of activation functions from earlier slide While building network we often make our network deeper by introducing new layers rather than wider by increasing neurons in layer. Increasing neuron just increases the number of trainable parameters. While making it deeper or adding new layers helps network in learning hierarchical structure. Hierarchical structure as in low level details like lines and edges to mid level details like shapes to high level concepts like head and body. The output layer depends on type of problem. If we have classification problem then the number of neurons are same as number of classes. If the problem is regression then output layer is sum of all previous layer neurons. By increasing number of hidden layer model complexity is increases. i.e it is capable of learning complex data. But also increases risk of overfitting.
  6. We first feed in the input data in vector form . Then we feed it to network. Its basically a series of matrix multiplication The data from input is multiplied by weights and bias is added. Then we apply non linearity like the Relu. This operation is repeated through every hidden layer. Finally when output is passed through output layer. This were we compare the output of neural network to the expected output or the label and compute the error. We then compute partial derivative with respect to weight in each layer and going back recursively. We then use this error derivative to change weights of that layers going back recursively. We repeat these steps until error reaches as small as possible. And this is how neural network learning is performed
  7. Number of trainable parameter are huge in Fully connected neural network. If we apply image input to FNN then number of trainable parameter even grows bigger. To address this issue we have CNN. Early layers of neural network are convolution layers with pooling layer in between. By introducing convolution layers, number of fully connected layers required for learning is low. What is a Convolution layer? We have small n x n matrices which we call filters. This filters are convoluted with the image to produces feature map. Convolution is operation similar to matrix multiplication except it is done in reverse manner. Filter is simultaneously multiplied with all parts of image to produce a feature map. Every conv layer has multiple trainable filters and hence output produced is stack of feature maps. As same filter is applied on various part of image the number of trainable parameters decreases. We then pass this stack of feature map through pooling layer. This pooling layer then reduces feature map to more manageable size. Type of pooling are max pooling where we take max value from small array of values. Another is avg pooling where we average out the values. This process is repeated for couple of layers. The output is then feed to a fully connected layer which takes these feature maps and produces the classification output. Various architectures have been proposed like the LeNet, Alex Net, VGG 16 with 16 layers, inception with 25 million parameters Microsoft Resnet has 152 layers and has residual connections. That is some conncetion to layers are skipped which again improves performance. Microsft Fast R-CNN
  8. How do we train model on sequence data. Data which has temporal property like speech data or weather forecasting or stock market price. For modelling sequences we have variation of Neural network know as RNN In this type of model the connection from hidden layer is given back to itself. Depending on type of requirement we have various architecture. First is Vanilla mode without RNN where we have fixed size input and fixed size output. Useful for image classification. Second model is fixed input variable output. Useful for caption generation for images Third: Sequence input fixed size output for task like sentiment analysis. Fourth Sequence input sequence output. For machine translation Last Synched sequence input output for task like video labeling. Also used for semantic similarity, where we have two RNN and output of both of them is passed through single layer which output related ness score.
  9. These kind of networks have been used for image upsampling, image completion, image generation from text