SlideShare une entreprise Scribd logo
1  sur  70
Deep Learning Jump Start
Michele Toni, 20 May 2017
Collegio Universitario Bertoni, Milano
Credits to Tommaso Matassini
About me
● M.Sc. in Computer Engineer for Business Administration at Università di Pisa
● 2 years as backend software developer.
● 1+ years as AI team member at Cynny.
More about Cynny: Morphcast site, Cynny Italian site, last public presentation
Today programme
● Deep Learning Showcase
● What is deep learning and how it works
○ Definitions
○ Neural Networks
○ Deep Learning
● How to start with deep learning
● Live demo: image classification Dogs Vs Cats with NVidia Digits
Deep Learning Showcase
Deep Learning applications
Perception: recognizing what's in an image, what people are saying when they are
talking on their phone, helping robots explore the world and interact with it.
Images
Videos
Text
NLP
Music Other
Image Classification
[Try this online with CaffeJS]
Object Detection - 1/2
[Source: Awesome Deep Vision]
Object Detection - 2/2
[Source: DetectNet by Nvidia]
Image Segmentation
[Source: SegNet Online Demo]
Image Captioning
[Source: MS COCO Captioning Challenge 2015]
Image Captioning - Facebook easy approach
[Source: The Verge article]
Neural Art - DeepDream 1/3
[Source: Google Inceptionism]
Neural Art - DeepDream 2/3
[Source: L’Altra Toscana: Garfagnana]
Neural Art - DeepDream 3/3
Neural Art - Style Transfer 1/2
StyleContent
Neural Art - Style Transfer 2/2
[Try this: DeepDream, Prisma, Vinci]
Neural Art - Deep Photo Style Transfer
[Source Code and details: DeepPhoto Github]
Text Generation - Hemingway style
[Source: Hemingway style and Super Mario level generation]
Sequence2Sequence - Language translation
[Source: Attention and Memory in Deep Learning and NLP]
Sequence2Sequence - Chat bot
[Source: ChatBots with seq2seq, seq2seq Github]
Music Generation - Google Magenta and others
[Google Magenta Song, Fake Beatles Song, DeepBach by Sony CSL Music]
Generative Adversarial Network - pix2pix
[Try this: pix2pix Demo]
Generative Adversarial Network - CycleGAN
[Source code and details: CycleGAN Github]
Reinforcement learning - Atari Breakout
[Atari Breakout Video, Flappy Bird, OpenAI Gym]
Image analysis (old) approach: Computer Vision
HOG Face detector
[Source: dlib site]
Local Binary Pattern
[Source]
Why we use Deep Learning
[Source: Nervana Systems]
What is Deep Learning
And
how it works
Definitions
AI Vs Machine Learning Vs Deep Learning
[Source: NVidia Blog]
Artificial Intelligence definition
Artificial intelligence (AI) is an area of computer science that emphasizes the
creation of intelligent machines that work and react like humans.
Some of the activities computers with artificial intelligence are designed for
include:
● Speech recognition
● Learning
● Planning
● Problem solving
[Source: Techopedia]
Machine Learning definition
Machine learning according to Arthur Samuel in 1959, gives "computers the
ability to learn without being explicitly programmed."
It explores the study and construction of algorithms that can learn from and
make predictions on data – such algorithms overcome following strictly
static program instructions by making data-driven predictions or decisions,
through building a model from sample inputs.
[Source: Wikipedia]
Types of learning
● Supervised learning: learn to predict an output when given an input
vector. We know the correct matching between input and output.
● Reinforcement learning: learn to select an action to maximize payoff.
● Unsupervised learning: discover a good internal representation of the
input. There is no known matching between input and output.
[Source: Geoffrey Hinton Neural Networks Coursera Course]
Types of learning: Supervised Learning
Each training case consists of an input vector x and a target ouput t.
● Regression: The target is a real number, e.g. the value of a stock, the
temperature.
● Classification: the target is a class label. E.g. from a given image tell if it
represents a cat or a dog.
[Source: Geoffrey Hinton Neural Networks Coursera Course]
Types of learning: Reinforcement Learning
● The output is an action or a sequence of actions and the only
supervisory signal is an occasional scalar reward. (No one tells which is
the correct action at each step, this has to be learned).
● The goal in selecting each action is to maximize the expected sum of
future rewards.
● Reinforcement learning is difficult, because the rewards can be delayed
and it is hard to know when we are wrong or right.
[Source: Geoffrey Hinton Neural Networks Coursera Course]
Types of learning: Unsupervised Learning 1/2
● Someone doesn’t consider unsupervised learning among the machine
learning techniques because it isn’t trained with input-output mapping.
● A typical example is clustering. E.g. to better visualize the inputs, to
study a problem, to prepare the data for a successive phase using
supervised or reinforcement learning.
[Source: Geoffrey Hinton Neural Networks Coursera Course]
Types of learning: Unsupervised Learning 2/2
[Source: T-Sne Visualization]
Neural Networks
Biological neuron
[Source: Stanford CS231n Course]
Artificial neuron
[Source: Stanford CS231n Course]
Common non linear activation functions
[Source: Machine Learning for artists]
Examples of artificial neural network
[Source: Stanford CS231n Course]
What is a supervised learning model
Model: y = f(x; W)
f is a way to use numerical parameters W (called weights), to map each input x
into a predicted output y.
Learning: the procedure that adjusting the parameters W aims to reduce the
discrepancy between y (model output) and t (target output) for each training
sample.
Example of error function (MSE):
[Source: Geoffrey Hinton Neural Networks Coursera Course]
Training example with linear regression
Problem: we want to predict the price of a house knowing the area.
We have this data (our training dataset):
[Source: Visual and Interactive view of the basic of neural networks]
Linear regression model
[Source: Visual and Interactive view of the basic of neural networks, Wikipedia]
Error (MSE):
Linear regression model training - 1/2
[Source: Visual and Interactive view of the basic of neural networks]
Manual
Descending the gradient of the error (simplified)
[Source: Quora question]
Descending the gradient of the error (reality)
[Source]
Linear regression model training - 2/2
[Source: Visual and Interactive view of the basic of neural networks]
Gradient Descent in action
Deep Learning
Deep Learning definition
“A family of learning methods that use deep architectures to learn high-level
feature representations”.
Examples of deep learning:
● Convolutional neural networks (for images)
● LSTM networks (for sequences like text and music)
[Source: Neural Machine Translation by Jointly Learning to Align and Translate]
Convolutional Neural Network layers
[Source: Stanford CS231n Course, in browser demo]
Convolution - 1/2
● Doesn’t matter where the cat is
● Different position, same cat
● We can share the weights!
[Source: Udacity Deep Learning Course by Google]
Convolution - 2/2
[Source: Stanford CS231n Course]
Graphical Demo
Pooling
[Source: Stanford CS231n Course]
CNN architecture: AlexNet (2012)
[Source: Visualize Neurons from Deep Models]
Convolutional Neural Networks recap
[Source: Siraj Raval Youtube Channel]
How to start with Deep Learning
What you need to train a CNN
DL Framework
Image Dataset Model structure
What you need to run a prediction
DL Framework
Model with trained weights
Datasets for specific tasks and challenges
Common models
View common model architectures online
Name Year Imagenet Top-5 Error #Parameters
Alexnet 2012 16,4 % 60 M
ZF 2013 11,7 % 16 M
GoogleNet 2014 6,7 % 7 M
VGG 2014 7,3 % 138 M
ResNet 2015 3,57 % 60 M
Inception-V4 2016 3,08 % 42 M
Squeezenet 2016 < 19,7 % ~ 1 M
Frameworks (very short list)
Name First release Main contributors Languages
Caffe / Caffe2 2013 / 2017 1 Berkeley University,
2 Facebook, Nvidia
Python, C++, Matlab
TensorFlow
(+ Keras API)
2015 Google Python, C++, Java, Go
Mxnet 2015 DMLC Python, Scala, Matlab,
C++, R, Julia, Go, JS
Torch 2002 (v1), 2015 (v7) Facebook, Twitter,
Google
LUA, C++
Live demo: Dogs Vs Cats
Live demo: Dogs Vs Cats
● Dataset: kaggle competition Dogs Vs Cats
● CNN Framework: Caffe + NVidia DIGITS
● Hardware: CUDA powered notebook (video card NVidia 970m)
● Model: Alexnet
Playground
Some additional AI playground links
DeepTraffic (simple self driving car training by MIT, with leaderboard)
AI Experiments with Google (e.g. AutoDraw, AI Duet)
TensorFlow Playground (try and visualize training)
Useful links to learn
Machine Learning is fun (intuitions behind how deep learning works)
Distill.pub (graphical and interactive paper publications)
Deep Learning Book by Yoshua Bengio
Neural Network Zoo (overview of neural networks architectures)
Dev Blog Nvidia - Parallel For All
9 Deep Learning Papers you need to know about
Awesome Deep Vision (Github papers repository)
Courses
Machine Learning by Andrew Ng (Coursera)
Neural Networks for Machine Learning (Coursera)
Deep Learning by Google (Udacity)
Deep Learning Nanodegree Foundation (Udacity)
Convolutional Neural Networks for Visual Recognition (Stanford)
Creative applications of deep learning with Tensorflow (Kadenze)
Other
Kaggle (machine learning competitions)
OpenAI Gym (environments and challenges to train reinforcement learning
models)
Google.ai
Thank you!

Contenu connexe

Tendances

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 - Overview of my work II
Deep Learning - Overview of my work IIDeep Learning - Overview of my work II
Deep Learning - Overview of my work IIMohamed Loey
 
Diving into Deep Learning (Silicon Valley Code Camp 2017)
Diving into Deep Learning (Silicon Valley Code Camp 2017)Diving into Deep Learning (Silicon Valley Code Camp 2017)
Diving into Deep Learning (Silicon Valley Code Camp 2017)Oswald Campesato
 
Introduction to Deep learning
Introduction to Deep learningIntroduction to Deep learning
Introduction to Deep learningleopauly
 
Synthetic dialogue generation with Deep Learning
Synthetic dialogue generation with Deep LearningSynthetic dialogue generation with Deep Learning
Synthetic dialogue generation with Deep LearningS N
 
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 ApproachMaurizio Calo Caligaris
 
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
 
Machine Learning and Deep Learning with R
Machine Learning and Deep Learning with RMachine Learning and Deep Learning with R
Machine Learning and Deep Learning with RPoo Kuan Hoong
 
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
 
BigDL webinar - Deep Learning Library for Spark
BigDL webinar - Deep Learning Library for SparkBigDL webinar - Deep Learning Library for Spark
BigDL webinar - Deep Learning Library for SparkDESMOND YUEN
 
[2A4]DeepLearningAtNAVER
[2A4]DeepLearningAtNAVER[2A4]DeepLearningAtNAVER
[2A4]DeepLearningAtNAVERNAVER D2
 
"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
 
Deep Learning: Application Landscape - March 2018
Deep Learning: Application Landscape - March 2018Deep Learning: Application Landscape - March 2018
Deep Learning: Application Landscape - March 2018Grigory Sapunov
 
Deep Neural Networks 
that talk (Back)… with style
Deep Neural Networks 
that talk (Back)… with styleDeep Neural Networks 
that talk (Back)… with style
Deep Neural Networks 
that talk (Back)… with styleRoelof Pieters
 
Using Deep Learning to do Real-Time Scoring in Practical Applications - 2015-...
Using Deep Learning to do Real-Time Scoring in Practical Applications - 2015-...Using Deep Learning to do Real-Time Scoring in Practical Applications - 2015-...
Using Deep Learning to do Real-Time Scoring in Practical Applications - 2015-...Greg Makowski
 
Deep Learning for Robotics
Deep Learning for RoboticsDeep Learning for Robotics
Deep Learning for RoboticsIntel Nervana
 
What is Deep Learning | Deep Learning Simplified | Deep Learning Tutorial | E...
What is Deep Learning | Deep Learning Simplified | Deep Learning Tutorial | E...What is Deep Learning | Deep Learning Simplified | Deep Learning Tutorial | E...
What is Deep Learning | Deep Learning Simplified | Deep Learning Tutorial | E...Edureka!
 
Neural networks and deep learning
Neural networks and deep learningNeural networks and deep learning
Neural networks and deep learningJörgen Sandig
 

Tendances (20)

Deep Learning: a birds eye view
Deep Learning: a birds eye viewDeep Learning: a birds eye view
Deep Learning: a birds eye view
 
Tutorial on Deep Learning
Tutorial on Deep LearningTutorial on Deep Learning
Tutorial on Deep Learning
 
Deep Learning - Overview of my work II
Deep Learning - Overview of my work IIDeep Learning - Overview of my work II
Deep Learning - Overview of my work II
 
Diving into Deep Learning (Silicon Valley Code Camp 2017)
Diving into Deep Learning (Silicon Valley Code Camp 2017)Diving into Deep Learning (Silicon Valley Code Camp 2017)
Diving into Deep Learning (Silicon Valley Code Camp 2017)
 
Introduction to Deep learning
Introduction to Deep learningIntroduction to Deep learning
Introduction to Deep learning
 
Synthetic dialogue generation with Deep Learning
Synthetic dialogue generation with Deep LearningSynthetic dialogue generation with Deep Learning
Synthetic dialogue generation with Deep 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
 
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
 
Machine Learning and Deep Learning with R
Machine Learning and Deep Learning with RMachine Learning and Deep Learning with R
Machine Learning and Deep Learning with R
 
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
 
BigDL webinar - Deep Learning Library for Spark
BigDL webinar - Deep Learning Library for SparkBigDL webinar - Deep Learning Library for Spark
BigDL webinar - Deep Learning Library for Spark
 
[2A4]DeepLearningAtNAVER
[2A4]DeepLearningAtNAVER[2A4]DeepLearningAtNAVER
[2A4]DeepLearningAtNAVER
 
"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...
 
Deep Learning: Application Landscape - March 2018
Deep Learning: Application Landscape - March 2018Deep Learning: Application Landscape - March 2018
Deep Learning: Application Landscape - March 2018
 
Deep Neural Networks 
that talk (Back)… with style
Deep Neural Networks 
that talk (Back)… with styleDeep Neural Networks 
that talk (Back)… with style
Deep Neural Networks 
that talk (Back)… with style
 
Using Deep Learning to do Real-Time Scoring in Practical Applications - 2015-...
Using Deep Learning to do Real-Time Scoring in Practical Applications - 2015-...Using Deep Learning to do Real-Time Scoring in Practical Applications - 2015-...
Using Deep Learning to do Real-Time Scoring in Practical Applications - 2015-...
 
Introduction to deep learning
Introduction to deep learningIntroduction to deep learning
Introduction to deep learning
 
Deep Learning for Robotics
Deep Learning for RoboticsDeep Learning for Robotics
Deep Learning for Robotics
 
What is Deep Learning | Deep Learning Simplified | Deep Learning Tutorial | E...
What is Deep Learning | Deep Learning Simplified | Deep Learning Tutorial | E...What is Deep Learning | Deep Learning Simplified | Deep Learning Tutorial | E...
What is Deep Learning | Deep Learning Simplified | Deep Learning Tutorial | E...
 
Neural networks and deep learning
Neural networks and deep learningNeural networks and deep learning
Neural networks and deep learning
 

Similaire à Deep Learning Jump Start

Slides galvin-widjaja
Slides galvin-widjajaSlides galvin-widjaja
Slides galvin-widjajaCodePolitan
 
Deep Learning with CNTK
Deep Learning with CNTKDeep Learning with CNTK
Deep Learning with CNTKAshish Jaiman
 
Image Classification and Annotation Using Deep Learning
Image Classification and Annotation Using Deep LearningImage Classification and Annotation Using Deep Learning
Image Classification and Annotation Using Deep LearningIRJET Journal
 
The Frontier of Deep Learning in 2020 and Beyond
The Frontier of Deep Learning in 2020 and BeyondThe Frontier of Deep Learning in 2020 and Beyond
The Frontier of Deep Learning in 2020 and BeyondNUS-ISS
 
Enhance your java applications with deep learning using deep netts
Enhance your java applications with deep learning using deep nettsEnhance your java applications with deep learning using deep netts
Enhance your java applications with deep learning using deep nettsZoran Sevarac, PhD
 
Crafting Recommenders: the Shallow and the Deep of it!
Crafting Recommenders: the Shallow and the Deep of it! Crafting Recommenders: the Shallow and the Deep of it!
Crafting Recommenders: the Shallow and the Deep of it! Sudeep Das, Ph.D.
 
How to use transfer learning to bootstrap image classification and question a...
How to use transfer learning to bootstrap image classification and question a...How to use transfer learning to bootstrap image classification and question a...
How to use transfer learning to bootstrap image classification and question a...Wee Hyong Tok
 
Kaz Sato, Evangelist, Google at MLconf ATL 2016
Kaz Sato, Evangelist, Google at MLconf ATL 2016Kaz Sato, Evangelist, Google at MLconf ATL 2016
Kaz Sato, Evangelist, Google at MLconf ATL 2016MLconf
 
data-science-pdf-16588.pdf
data-science-pdf-16588.pdfdata-science-pdf-16588.pdf
data-science-pdf-16588.pdfvkharish18
 
Deep Learning and the state of AI / 2016
Deep Learning and the state of AI / 2016Deep Learning and the state of AI / 2016
Deep Learning and the state of AI / 2016Grigory Sapunov
 
لموعد الإثنين 03 يناير 2022 143 مبادرة #تواصل_تطوير المحاضرة ال 143 من المباد...
لموعد الإثنين 03 يناير 2022 143 مبادرة #تواصل_تطوير المحاضرة ال 143 من المباد...لموعد الإثنين 03 يناير 2022 143 مبادرة #تواصل_تطوير المحاضرة ال 143 من المباد...
لموعد الإثنين 03 يناير 2022 143 مبادرة #تواصل_تطوير المحاضرة ال 143 من المباد...Egyptian Engineers Association
 
OReilly AI Transfer Learning
OReilly AI Transfer LearningOReilly AI Transfer Learning
OReilly AI Transfer LearningDanielle Dean
 
Challenges of Deep Learning in Computer Vision Webinar - Tessellate Imaging
Challenges of Deep Learning in Computer Vision Webinar - Tessellate ImagingChallenges of Deep Learning in Computer Vision Webinar - Tessellate Imaging
Challenges of Deep Learning in Computer Vision Webinar - Tessellate ImagingAdhesh Shrivastava
 
MachinaFiesta: A Vision into Machine Learning 🚀
MachinaFiesta: A Vision into Machine Learning 🚀MachinaFiesta: A Vision into Machine Learning 🚀
MachinaFiesta: A Vision into Machine Learning 🚀GDSCNiT
 
HABIB FIGA GUYE {BULE HORA UNIVERSITY}(habibifiga@gmail.com
HABIB FIGA GUYE {BULE HORA UNIVERSITY}(habibifiga@gmail.comHABIB FIGA GUYE {BULE HORA UNIVERSITY}(habibifiga@gmail.com
HABIB FIGA GUYE {BULE HORA UNIVERSITY}(habibifiga@gmail.comHABIB FIGA GUYE
 

Similaire à Deep Learning Jump Start (20)

Slides galvin-widjaja
Slides galvin-widjajaSlides galvin-widjaja
Slides galvin-widjaja
 
Deep Learning with CNTK
Deep Learning with CNTKDeep Learning with CNTK
Deep Learning with CNTK
 
Machine learning workshop
Machine learning workshopMachine learning workshop
Machine learning workshop
 
Image Classification and Annotation Using Deep Learning
Image Classification and Annotation Using Deep LearningImage Classification and Annotation Using Deep Learning
Image Classification and Annotation Using Deep Learning
 
Null
NullNull
Null
 
The Frontier of Deep Learning in 2020 and Beyond
The Frontier of Deep Learning in 2020 and BeyondThe Frontier of Deep Learning in 2020 and Beyond
The Frontier of Deep Learning in 2020 and Beyond
 
Enhance your java applications with deep learning using deep netts
Enhance your java applications with deep learning using deep nettsEnhance your java applications with deep learning using deep netts
Enhance your java applications with deep learning using deep netts
 
Crafting Recommenders: the Shallow and the Deep of it!
Crafting Recommenders: the Shallow and the Deep of it! Crafting Recommenders: the Shallow and the Deep of it!
Crafting Recommenders: the Shallow and the Deep of it!
 
How to use transfer learning to bootstrap image classification and question a...
How to use transfer learning to bootstrap image classification and question a...How to use transfer learning to bootstrap image classification and question a...
How to use transfer learning to bootstrap image classification and question a...
 
Kaz Sato, Evangelist, Google at MLconf ATL 2016
Kaz Sato, Evangelist, Google at MLconf ATL 2016Kaz Sato, Evangelist, Google at MLconf ATL 2016
Kaz Sato, Evangelist, Google at MLconf ATL 2016
 
MILA DL & RL summer school highlights
MILA DL & RL summer school highlights MILA DL & RL summer school highlights
MILA DL & RL summer school highlights
 
data-science-pdf-16588.pdf
data-science-pdf-16588.pdfdata-science-pdf-16588.pdf
data-science-pdf-16588.pdf
 
Deep Learning and the state of AI / 2016
Deep Learning and the state of AI / 2016Deep Learning and the state of AI / 2016
Deep Learning and the state of AI / 2016
 
لموعد الإثنين 03 يناير 2022 143 مبادرة #تواصل_تطوير المحاضرة ال 143 من المباد...
لموعد الإثنين 03 يناير 2022 143 مبادرة #تواصل_تطوير المحاضرة ال 143 من المباد...لموعد الإثنين 03 يناير 2022 143 مبادرة #تواصل_تطوير المحاضرة ال 143 من المباد...
لموعد الإثنين 03 يناير 2022 143 مبادرة #تواصل_تطوير المحاضرة ال 143 من المباد...
 
OReilly AI Transfer Learning
OReilly AI Transfer LearningOReilly AI Transfer Learning
OReilly AI Transfer Learning
 
Challenges of Deep Learning in Computer Vision Webinar - Tessellate Imaging
Challenges of Deep Learning in Computer Vision Webinar - Tessellate ImagingChallenges of Deep Learning in Computer Vision Webinar - Tessellate Imaging
Challenges of Deep Learning in Computer Vision Webinar - Tessellate Imaging
 
AI and Deep Learning
AI and Deep Learning AI and Deep Learning
AI and Deep Learning
 
MachinaFiesta: A Vision into Machine Learning 🚀
MachinaFiesta: A Vision into Machine Learning 🚀MachinaFiesta: A Vision into Machine Learning 🚀
MachinaFiesta: A Vision into Machine Learning 🚀
 
HABIB FIGA GUYE {BULE HORA UNIVERSITY}(habibifiga@gmail.com
HABIB FIGA GUYE {BULE HORA UNIVERSITY}(habibifiga@gmail.comHABIB FIGA GUYE {BULE HORA UNIVERSITY}(habibifiga@gmail.com
HABIB FIGA GUYE {BULE HORA UNIVERSITY}(habibifiga@gmail.com
 
User-centered open source
User-centered open sourceUser-centered open source
User-centered open source
 

Dernier

Developing An App To Navigate The Roads of Brazil
Developing An App To Navigate The Roads of BrazilDeveloping An App To Navigate The Roads of Brazil
Developing An App To Navigate The Roads of BrazilV3cube
 
GenCyber Cyber Security Day Presentation
GenCyber Cyber Security Day PresentationGenCyber Cyber Security Day Presentation
GenCyber Cyber Security Day PresentationMichael W. Hawkins
 
Bajaj Allianz Life Insurance Company - Insurer Innovation Award 2024
Bajaj Allianz Life Insurance Company - Insurer Innovation Award 2024Bajaj Allianz Life Insurance Company - Insurer Innovation Award 2024
Bajaj Allianz Life Insurance Company - Insurer Innovation Award 2024The Digital Insurer
 
AWS Community Day CPH - Three problems of Terraform
AWS Community Day CPH - Three problems of TerraformAWS Community Day CPH - Three problems of Terraform
AWS Community Day CPH - Three problems of TerraformAndrey Devyatkin
 
The 7 Things I Know About Cyber Security After 25 Years | April 2024
The 7 Things I Know About Cyber Security After 25 Years | April 2024The 7 Things I Know About Cyber Security After 25 Years | April 2024
The 7 Things I Know About Cyber Security After 25 Years | April 2024Rafal Los
 
Apidays Singapore 2024 - Building Digital Trust in a Digital Economy by Veron...
Apidays Singapore 2024 - Building Digital Trust in a Digital Economy by Veron...Apidays Singapore 2024 - Building Digital Trust in a Digital Economy by Veron...
Apidays Singapore 2024 - Building Digital Trust in a Digital Economy by Veron...apidays
 
Handwritten Text Recognition for manuscripts and early printed texts
Handwritten Text Recognition for manuscripts and early printed textsHandwritten Text Recognition for manuscripts and early printed texts
Handwritten Text Recognition for manuscripts and early printed textsMaria Levchenko
 
Driving Behavioral Change for Information Management through Data-Driven Gree...
Driving Behavioral Change for Information Management through Data-Driven Gree...Driving Behavioral Change for Information Management through Data-Driven Gree...
Driving Behavioral Change for Information Management through Data-Driven Gree...Enterprise Knowledge
 
Boost Fertility New Invention Ups Success Rates.pdf
Boost Fertility New Invention Ups Success Rates.pdfBoost Fertility New Invention Ups Success Rates.pdf
Boost Fertility New Invention Ups Success Rates.pdfsudhanshuwaghmare1
 
Strategize a Smooth Tenant-to-tenant Migration and Copilot Takeoff
Strategize a Smooth Tenant-to-tenant Migration and Copilot TakeoffStrategize a Smooth Tenant-to-tenant Migration and Copilot Takeoff
Strategize a Smooth Tenant-to-tenant Migration and Copilot Takeoffsammart93
 
Finology Group – Insurtech Innovation Award 2024
Finology Group – Insurtech Innovation Award 2024Finology Group – Insurtech Innovation Award 2024
Finology Group – Insurtech Innovation Award 2024The Digital Insurer
 
Mastering MySQL Database Architecture: Deep Dive into MySQL Shell and MySQL R...
Mastering MySQL Database Architecture: Deep Dive into MySQL Shell and MySQL R...Mastering MySQL Database Architecture: Deep Dive into MySQL Shell and MySQL R...
Mastering MySQL Database Architecture: Deep Dive into MySQL Shell and MySQL R...Miguel Araújo
 
Connector Corner: Accelerate revenue generation using UiPath API-centric busi...
Connector Corner: Accelerate revenue generation using UiPath API-centric busi...Connector Corner: Accelerate revenue generation using UiPath API-centric busi...
Connector Corner: Accelerate revenue generation using UiPath API-centric busi...DianaGray10
 
Strategies for Landing an Oracle DBA Job as a Fresher
Strategies for Landing an Oracle DBA Job as a FresherStrategies for Landing an Oracle DBA Job as a Fresher
Strategies for Landing an Oracle DBA Job as a FresherRemote DBA Services
 
[2024]Digital Global Overview Report 2024 Meltwater.pdf
[2024]Digital Global Overview Report 2024 Meltwater.pdf[2024]Digital Global Overview Report 2024 Meltwater.pdf
[2024]Digital Global Overview Report 2024 Meltwater.pdfhans926745
 
Automating Google Workspace (GWS) & more with Apps Script
Automating Google Workspace (GWS) & more with Apps ScriptAutomating Google Workspace (GWS) & more with Apps Script
Automating Google Workspace (GWS) & more with Apps Scriptwesley chun
 
What Are The Drone Anti-jamming Systems Technology?
What Are The Drone Anti-jamming Systems Technology?What Are The Drone Anti-jamming Systems Technology?
What Are The Drone Anti-jamming Systems Technology?Antenna Manufacturer Coco
 
Apidays New York 2024 - The value of a flexible API Management solution for O...
Apidays New York 2024 - The value of a flexible API Management solution for O...Apidays New York 2024 - The value of a flexible API Management solution for O...
Apidays New York 2024 - The value of a flexible API Management solution for O...apidays
 
Strategies for Unlocking Knowledge Management in Microsoft 365 in the Copilot...
Strategies for Unlocking Knowledge Management in Microsoft 365 in the Copilot...Strategies for Unlocking Knowledge Management in Microsoft 365 in the Copilot...
Strategies for Unlocking Knowledge Management in Microsoft 365 in the Copilot...Drew Madelung
 
presentation ICT roal in 21st century education
presentation ICT roal in 21st century educationpresentation ICT roal in 21st century education
presentation ICT roal in 21st century educationjfdjdjcjdnsjd
 

Dernier (20)

Developing An App To Navigate The Roads of Brazil
Developing An App To Navigate The Roads of BrazilDeveloping An App To Navigate The Roads of Brazil
Developing An App To Navigate The Roads of Brazil
 
GenCyber Cyber Security Day Presentation
GenCyber Cyber Security Day PresentationGenCyber Cyber Security Day Presentation
GenCyber Cyber Security Day Presentation
 
Bajaj Allianz Life Insurance Company - Insurer Innovation Award 2024
Bajaj Allianz Life Insurance Company - Insurer Innovation Award 2024Bajaj Allianz Life Insurance Company - Insurer Innovation Award 2024
Bajaj Allianz Life Insurance Company - Insurer Innovation Award 2024
 
AWS Community Day CPH - Three problems of Terraform
AWS Community Day CPH - Three problems of TerraformAWS Community Day CPH - Three problems of Terraform
AWS Community Day CPH - Three problems of Terraform
 
The 7 Things I Know About Cyber Security After 25 Years | April 2024
The 7 Things I Know About Cyber Security After 25 Years | April 2024The 7 Things I Know About Cyber Security After 25 Years | April 2024
The 7 Things I Know About Cyber Security After 25 Years | April 2024
 
Apidays Singapore 2024 - Building Digital Trust in a Digital Economy by Veron...
Apidays Singapore 2024 - Building Digital Trust in a Digital Economy by Veron...Apidays Singapore 2024 - Building Digital Trust in a Digital Economy by Veron...
Apidays Singapore 2024 - Building Digital Trust in a Digital Economy by Veron...
 
Handwritten Text Recognition for manuscripts and early printed texts
Handwritten Text Recognition for manuscripts and early printed textsHandwritten Text Recognition for manuscripts and early printed texts
Handwritten Text Recognition for manuscripts and early printed texts
 
Driving Behavioral Change for Information Management through Data-Driven Gree...
Driving Behavioral Change for Information Management through Data-Driven Gree...Driving Behavioral Change for Information Management through Data-Driven Gree...
Driving Behavioral Change for Information Management through Data-Driven Gree...
 
Boost Fertility New Invention Ups Success Rates.pdf
Boost Fertility New Invention Ups Success Rates.pdfBoost Fertility New Invention Ups Success Rates.pdf
Boost Fertility New Invention Ups Success Rates.pdf
 
Strategize a Smooth Tenant-to-tenant Migration and Copilot Takeoff
Strategize a Smooth Tenant-to-tenant Migration and Copilot TakeoffStrategize a Smooth Tenant-to-tenant Migration and Copilot Takeoff
Strategize a Smooth Tenant-to-tenant Migration and Copilot Takeoff
 
Finology Group – Insurtech Innovation Award 2024
Finology Group – Insurtech Innovation Award 2024Finology Group – Insurtech Innovation Award 2024
Finology Group – Insurtech Innovation Award 2024
 
Mastering MySQL Database Architecture: Deep Dive into MySQL Shell and MySQL R...
Mastering MySQL Database Architecture: Deep Dive into MySQL Shell and MySQL R...Mastering MySQL Database Architecture: Deep Dive into MySQL Shell and MySQL R...
Mastering MySQL Database Architecture: Deep Dive into MySQL Shell and MySQL R...
 
Connector Corner: Accelerate revenue generation using UiPath API-centric busi...
Connector Corner: Accelerate revenue generation using UiPath API-centric busi...Connector Corner: Accelerate revenue generation using UiPath API-centric busi...
Connector Corner: Accelerate revenue generation using UiPath API-centric busi...
 
Strategies for Landing an Oracle DBA Job as a Fresher
Strategies for Landing an Oracle DBA Job as a FresherStrategies for Landing an Oracle DBA Job as a Fresher
Strategies for Landing an Oracle DBA Job as a Fresher
 
[2024]Digital Global Overview Report 2024 Meltwater.pdf
[2024]Digital Global Overview Report 2024 Meltwater.pdf[2024]Digital Global Overview Report 2024 Meltwater.pdf
[2024]Digital Global Overview Report 2024 Meltwater.pdf
 
Automating Google Workspace (GWS) & more with Apps Script
Automating Google Workspace (GWS) & more with Apps ScriptAutomating Google Workspace (GWS) & more with Apps Script
Automating Google Workspace (GWS) & more with Apps Script
 
What Are The Drone Anti-jamming Systems Technology?
What Are The Drone Anti-jamming Systems Technology?What Are The Drone Anti-jamming Systems Technology?
What Are The Drone Anti-jamming Systems Technology?
 
Apidays New York 2024 - The value of a flexible API Management solution for O...
Apidays New York 2024 - The value of a flexible API Management solution for O...Apidays New York 2024 - The value of a flexible API Management solution for O...
Apidays New York 2024 - The value of a flexible API Management solution for O...
 
Strategies for Unlocking Knowledge Management in Microsoft 365 in the Copilot...
Strategies for Unlocking Knowledge Management in Microsoft 365 in the Copilot...Strategies for Unlocking Knowledge Management in Microsoft 365 in the Copilot...
Strategies for Unlocking Knowledge Management in Microsoft 365 in the Copilot...
 
presentation ICT roal in 21st century education
presentation ICT roal in 21st century educationpresentation ICT roal in 21st century education
presentation ICT roal in 21st century education
 

Deep Learning Jump Start

  • 1. Deep Learning Jump Start Michele Toni, 20 May 2017 Collegio Universitario Bertoni, Milano Credits to Tommaso Matassini
  • 2. About me ● M.Sc. in Computer Engineer for Business Administration at Università di Pisa ● 2 years as backend software developer. ● 1+ years as AI team member at Cynny. More about Cynny: Morphcast site, Cynny Italian site, last public presentation
  • 3. Today programme ● Deep Learning Showcase ● What is deep learning and how it works ○ Definitions ○ Neural Networks ○ Deep Learning ● How to start with deep learning ● Live demo: image classification Dogs Vs Cats with NVidia Digits
  • 5. Deep Learning applications Perception: recognizing what's in an image, what people are saying when they are talking on their phone, helping robots explore the world and interact with it. Images Videos Text NLP Music Other
  • 6. Image Classification [Try this online with CaffeJS]
  • 7. Object Detection - 1/2 [Source: Awesome Deep Vision]
  • 8. Object Detection - 2/2 [Source: DetectNet by Nvidia]
  • 10. Image Captioning [Source: MS COCO Captioning Challenge 2015]
  • 11. Image Captioning - Facebook easy approach [Source: The Verge article]
  • 12. Neural Art - DeepDream 1/3 [Source: Google Inceptionism]
  • 13. Neural Art - DeepDream 2/3 [Source: L’Altra Toscana: Garfagnana]
  • 14. Neural Art - DeepDream 3/3
  • 15. Neural Art - Style Transfer 1/2 StyleContent
  • 16. Neural Art - Style Transfer 2/2 [Try this: DeepDream, Prisma, Vinci]
  • 17. Neural Art - Deep Photo Style Transfer [Source Code and details: DeepPhoto Github]
  • 18. Text Generation - Hemingway style [Source: Hemingway style and Super Mario level generation]
  • 19. Sequence2Sequence - Language translation [Source: Attention and Memory in Deep Learning and NLP]
  • 20. Sequence2Sequence - Chat bot [Source: ChatBots with seq2seq, seq2seq Github]
  • 21. Music Generation - Google Magenta and others [Google Magenta Song, Fake Beatles Song, DeepBach by Sony CSL Music]
  • 22. Generative Adversarial Network - pix2pix [Try this: pix2pix Demo]
  • 23. Generative Adversarial Network - CycleGAN [Source code and details: CycleGAN Github]
  • 24. Reinforcement learning - Atari Breakout [Atari Breakout Video, Flappy Bird, OpenAI Gym]
  • 25. Image analysis (old) approach: Computer Vision HOG Face detector [Source: dlib site] Local Binary Pattern [Source]
  • 26. Why we use Deep Learning [Source: Nervana Systems]
  • 27. What is Deep Learning And how it works
  • 29. AI Vs Machine Learning Vs Deep Learning [Source: NVidia Blog]
  • 30. Artificial Intelligence definition Artificial intelligence (AI) is an area of computer science that emphasizes the creation of intelligent machines that work and react like humans. Some of the activities computers with artificial intelligence are designed for include: ● Speech recognition ● Learning ● Planning ● Problem solving [Source: Techopedia]
  • 31. Machine Learning definition Machine learning according to Arthur Samuel in 1959, gives "computers the ability to learn without being explicitly programmed." It explores the study and construction of algorithms that can learn from and make predictions on data – such algorithms overcome following strictly static program instructions by making data-driven predictions or decisions, through building a model from sample inputs. [Source: Wikipedia]
  • 32. Types of learning ● Supervised learning: learn to predict an output when given an input vector. We know the correct matching between input and output. ● Reinforcement learning: learn to select an action to maximize payoff. ● Unsupervised learning: discover a good internal representation of the input. There is no known matching between input and output. [Source: Geoffrey Hinton Neural Networks Coursera Course]
  • 33. Types of learning: Supervised Learning Each training case consists of an input vector x and a target ouput t. ● Regression: The target is a real number, e.g. the value of a stock, the temperature. ● Classification: the target is a class label. E.g. from a given image tell if it represents a cat or a dog. [Source: Geoffrey Hinton Neural Networks Coursera Course]
  • 34. Types of learning: Reinforcement Learning ● The output is an action or a sequence of actions and the only supervisory signal is an occasional scalar reward. (No one tells which is the correct action at each step, this has to be learned). ● The goal in selecting each action is to maximize the expected sum of future rewards. ● Reinforcement learning is difficult, because the rewards can be delayed and it is hard to know when we are wrong or right. [Source: Geoffrey Hinton Neural Networks Coursera Course]
  • 35. Types of learning: Unsupervised Learning 1/2 ● Someone doesn’t consider unsupervised learning among the machine learning techniques because it isn’t trained with input-output mapping. ● A typical example is clustering. E.g. to better visualize the inputs, to study a problem, to prepare the data for a successive phase using supervised or reinforcement learning. [Source: Geoffrey Hinton Neural Networks Coursera Course]
  • 36. Types of learning: Unsupervised Learning 2/2 [Source: T-Sne Visualization]
  • 40. Common non linear activation functions [Source: Machine Learning for artists]
  • 41. Examples of artificial neural network [Source: Stanford CS231n Course]
  • 42. What is a supervised learning model Model: y = f(x; W) f is a way to use numerical parameters W (called weights), to map each input x into a predicted output y. Learning: the procedure that adjusting the parameters W aims to reduce the discrepancy between y (model output) and t (target output) for each training sample. Example of error function (MSE): [Source: Geoffrey Hinton Neural Networks Coursera Course]
  • 43. Training example with linear regression Problem: we want to predict the price of a house knowing the area. We have this data (our training dataset): [Source: Visual and Interactive view of the basic of neural networks]
  • 44. Linear regression model [Source: Visual and Interactive view of the basic of neural networks, Wikipedia] Error (MSE):
  • 45. Linear regression model training - 1/2 [Source: Visual and Interactive view of the basic of neural networks] Manual
  • 46. Descending the gradient of the error (simplified) [Source: Quora question]
  • 47. Descending the gradient of the error (reality) [Source]
  • 48. Linear regression model training - 2/2 [Source: Visual and Interactive view of the basic of neural networks] Gradient Descent in action
  • 50. Deep Learning definition “A family of learning methods that use deep architectures to learn high-level feature representations”. Examples of deep learning: ● Convolutional neural networks (for images) ● LSTM networks (for sequences like text and music) [Source: Neural Machine Translation by Jointly Learning to Align and Translate]
  • 51. Convolutional Neural Network layers [Source: Stanford CS231n Course, in browser demo]
  • 52. Convolution - 1/2 ● Doesn’t matter where the cat is ● Different position, same cat ● We can share the weights! [Source: Udacity Deep Learning Course by Google]
  • 53. Convolution - 2/2 [Source: Stanford CS231n Course] Graphical Demo
  • 55. CNN architecture: AlexNet (2012) [Source: Visualize Neurons from Deep Models]
  • 56. Convolutional Neural Networks recap [Source: Siraj Raval Youtube Channel]
  • 57. How to start with Deep Learning
  • 58. What you need to train a CNN DL Framework Image Dataset Model structure
  • 59. What you need to run a prediction DL Framework Model with trained weights
  • 60. Datasets for specific tasks and challenges
  • 61. Common models View common model architectures online Name Year Imagenet Top-5 Error #Parameters Alexnet 2012 16,4 % 60 M ZF 2013 11,7 % 16 M GoogleNet 2014 6,7 % 7 M VGG 2014 7,3 % 138 M ResNet 2015 3,57 % 60 M Inception-V4 2016 3,08 % 42 M Squeezenet 2016 < 19,7 % ~ 1 M
  • 62. Frameworks (very short list) Name First release Main contributors Languages Caffe / Caffe2 2013 / 2017 1 Berkeley University, 2 Facebook, Nvidia Python, C++, Matlab TensorFlow (+ Keras API) 2015 Google Python, C++, Java, Go Mxnet 2015 DMLC Python, Scala, Matlab, C++, R, Julia, Go, JS Torch 2002 (v1), 2015 (v7) Facebook, Twitter, Google LUA, C++
  • 63. Live demo: Dogs Vs Cats
  • 64. Live demo: Dogs Vs Cats ● Dataset: kaggle competition Dogs Vs Cats ● CNN Framework: Caffe + NVidia DIGITS ● Hardware: CUDA powered notebook (video card NVidia 970m) ● Model: Alexnet
  • 66. Some additional AI playground links DeepTraffic (simple self driving car training by MIT, with leaderboard) AI Experiments with Google (e.g. AutoDraw, AI Duet) TensorFlow Playground (try and visualize training)
  • 67. Useful links to learn Machine Learning is fun (intuitions behind how deep learning works) Distill.pub (graphical and interactive paper publications) Deep Learning Book by Yoshua Bengio Neural Network Zoo (overview of neural networks architectures) Dev Blog Nvidia - Parallel For All 9 Deep Learning Papers you need to know about Awesome Deep Vision (Github papers repository)
  • 68. Courses Machine Learning by Andrew Ng (Coursera) Neural Networks for Machine Learning (Coursera) Deep Learning by Google (Udacity) Deep Learning Nanodegree Foundation (Udacity) Convolutional Neural Networks for Visual Recognition (Stanford) Creative applications of deep learning with Tensorflow (Kadenze)
  • 69. Other Kaggle (machine learning competitions) OpenAI Gym (environments and challenges to train reinforcement learning models) Google.ai

Notes de l'éditeur

  1. Deep learning is emerging as a central tool to solve perception problems in recent years. It's the state of the art having to do with computer vision and speech recognition. But there's more; increasingly, people are finding that deep learning is a much better tool to solve problems like discovering new medicines, understanding natural language, understanding documents, and for example, ranking them for search.
  2. HOG Image: https://www.researchgate.net/profile/Shadrokh_Samavi/publication/269074001/figure/fig1/AS:295521232146434@1447469160525/Fig-1-HOG-calculation-a-gradients-in-a-cell-b-histogram-of-gradients.png
  3. Esempio prezzo dell’affitto come output, in input metri quadrati, vicinanza al centro, numero di bagni. Flusso da input ad output con risposta corretta attraverso weights “magici”. Slide successiva come apprendere i valori dei pesi. Accennare a training, cosa definisco a questo punto e cosa devo fornire.
  4. Udacity gradient descent video: https://www.youtube.com/watch?v=7sxA5Ap8AWM&t=3m
  5. Anticipare feature di livello crescente/descrescente nella rete, es. Per gatto servono orecchie, occhi, ovali, linee, … ResNet 152.
  6. Stop al dropbout
  7. Imagenet, MS COCO, PASCAL, Places
  8. Alexnet, VGG, GoogleNet, ResNet, Inception V4, Squeezenet con anno, imagenet error, numero di layer (o #parametri)