SlideShare una empresa de Scribd logo
1 de 54
January 5, 2017 1
Deep Learning
Er. Shiva K. Shrestha, ME Computer, NCIT
Slide Credit
o Jeff Dean, Google, Large Scale Deep Learning
o Andrew Ng, Deep Learning
o Aditya Khosla & Joseph Lim, Visual Recognition through ML Competition
January 5, 2017 2
Structure
◦ General Questions of the World
◦ What is Deep Learning?
◦ Why Deep Learning?
◦ Deep Neural Network Architectures
◦ Deep Learning Applications
◦ Conclusions, Recommendations
January 5, 2017 3
How Can We Build More Intelligent Computer
Systems?
According to Jeff Dean, Google:
o Need to perceive and understand the world
o Basic speech and vision capabilities
o Language understanding
o User behavior prediction
o …
January 5, 2017 4
How can we do this?
According to Jeff Dean, Google:
o Cannot write algorithms for each task we want to accomplish
separately.
o Need to write general algorithms that learn from observations
o Can we build systems that:
o Generate understanding from raw data
o Solve difficult problems to improve products
o Minimize software engineering effort
January 5, 2017 5
Plenty of Data
o Text: trillions of words of English + other languages
o Visual: billions of images and videos
o Audio: thousands of hours of speech per day
o User Activity: queries, result page clicks, map requests, etc.
o Knowledge Graph: billions of labelled relation triples
o …
January 5, 2017 6
Image Models
January 5, 2017 7
What are these numbers?
January 5, 2017 8
What are all these words?
January 5, 2017 9
How about these words?
January 5, 2017 10
Textual Understanding
“This movie should have NEVER been made. From the poorly done
animation, to the beyond bad acting. I am not sure at what point the
people behind this movie said "Ok, looks good! Lets do it!" I was in
awe of how truly horrid this movie was.”
January 5, 2017 11
General Machine Learning Approaches
o Learning by labeled example: Supervised Learning
o e.g. An email spam detector
o amazingly effective if you have lots of examples
o Discovering patterns: Unsupervised Learning
o e.g. data clustering
o difficult in practice, but useful if you lack labeled examples
o Feedback right/wrong: Reinforcement Learning
o e.g. learning to play chess by winning or losing
o works well in some domains, becoming more important
January 5, 2017 12
Machine Learning
o For many of these problems, we have lots of data
o gives computers the ability to learn without being explicitly
programmed
January 5, 2017 13
Approaches
o Decision tree learning
o Association rule learning
o Artificial neural networks
o Deep learning
o Inductive logic programming
o Support vector machines
o Clustering
o Bayesian networks
Approaches …
o Reinforcement learning
o Representation learning
o Similarity and metric learning
o Sparse dictionary learning
o Genetic algorithms
o Rule-based machine learning
o Learning classifier systems
Typical Goal of Machine Learning
Label: “Motorcycle”
Suggest tags
Image search
…
Speech recognition
Music classification
Speaker identification
…
Web search
Anti-spam
Machine translation
…
text
audio
images/video
I/p O/p
ML
ML
ML
January 5, 2017 14
Basic Idea of Deep Learning
Is there some way to extract meaningful features from data
even without knowing the task to be performed?
Then, throw in some hierarchical ‘stuff’ to make it ‘deep’
January 5, 2017 15
What is Deep Learning?
o The modern reincarnation of ANNs from the 1980s and 90s.
o A collection of simple trainable mathematical units, which
collaborate to compute a complicated function.
oCompatible with (3) General ML Approaches
January 5, 2017 16
What is Deep Learning? (2)
o Loosely inspired by what (little) we know about the biological brain.
o AKA:
o Deep Structure Learning
o Hierarchical Learning
o Deep M/c Learning
January 5, 2017 17
Deep Learning Definitions
Deep learning is characterized as a class of machine learning algorithms that
o use a cascade of many layers of nonlinear processing units for feature
extraction and transformation.
o are based on the learning of multiple levels of features or representations of
the data.
o are part of the broader machine learning field of learning representations of
data.
o learn multiple levels of representations that correspond to different levels of
abstraction;
January 5, 2017 18
DL - Why is this hard?
You see this:
But the camera sees this:
January 5, 2017 19
Pixel-based Representation
Input
Raw image
Motorbikes
“Non”-Motorbikes
Learning
algorithm
pixel 1
pixel2
pixel 1
pixel 2
January 5, 2017 20
Pixel-based Representation (2)
Input
Motorbikes
“Non”-Motorbikes
Learning
algorithm
pixel 1
pixel2
pixel 1
pixel 2
Raw image
January 5, 2017 21
Pixel-based Representation (2)
Input Motorbikes
“Non”-Motorbikes
Learning
algorithm
pixel 1
pixel2
pixel 1
pixel 2
Raw image
January 5, 2017 22
What We Want
Input
Motorbikes
“Non”-Motorbikes
Learning
algorithm
pixel 1
pixel2
Feature
representation
handlebars
wheel
E.g., Does it have Handlebars? Wheels?
Handlebars
Wheels
Raw image Features
January 5, 2017 23
Some Feature Representations
SIFT Spin image
HoG
RIFT
Textons GLOH
January 5, 2017 24
Some Feature Representations (2)
SIFT Spin image
HoG
RIFT
Textons GLOH
Coming up with features is often difficult, time-
consuming, and requires expert knowledge.
January 5, 2017 25
The Brain:
Potential Motivation for Deep Learning
[Roe et al., 1992]
Auditory Cortex learns to see!
Auditory Cortex
January 5, 2017 26
The Brain adapts!
[BrainPort; Welsh & Blasch, 1997; Nagel et al., 2005; Constantine-Paton & Law, 2009]
Seeing with your Tongue Human Echolocation (Sonar)
Haptic belt: Direction Sense Implanting a 3rd Eye
January 5, 2017 27
Feature Learning Problem
Given a 14x14 image patch x, can represent it using 196 real numbers.
Problem: Can we find a learn a better feature vector to represent this?
255
98
93
87
89
91
48
…
January 5, 2017 28
Why Deep Learning?
Method Accuracy
Hessian + ESURF [Williems et al 2008] 38%
Harris3D + HOG/HOF [Laptev et al 2003,
2004]
45%
Cuboids + HOG/HOF [Dollar et al 2005,
Laptev 2004]
46%
Hessian + HOG/HOF [Laptev 2004, Williems
et al 2008]
46%
Dense + HOG / HOF [Laptev 2004] 47%
Cuboids + HOG3D [Klaser 2008, Dollar et al
2005]
46%
Unsupervised Feature Learning (DL) 52%
[Le, Zhou & Ng, 2011]
Task: Video Activity Recognition
January 5, 2017 29
Deep Neural Network Architectures
o GMDH: 1st DLN of 1965
o Convolutional NN
o Neural history compressor
o Recursive NN
o Long short-term memory (LSTM)
o Deep belief networks (DBN)
o Convolutional deep belief networks
o Large memory storage & retrieval NN
o Deep Boltzmann machines
o Stacked (de-noising) auto-encoders
o Deep stacking networks
o Tensor deep stacking networks
o Spike-and-slab RBMs
o Compound hierarchical-deep models
o Deep coding networks
o Deep Q-networks
o Networks with separate memory
structures
January 5, 2017 30
Neural Network (NN)
x1
x2
x3
+1 +1
Layer 1 Layer 2
Layer 4+1
Layer 3
4 layer network with 2 output units:
January 5, 2017 31
Unsupervised Feature Learning with a NN
x4
x5
x6
+1
x1
x2
x3
+1
a1
a2
a3
+1
b1
b2
b3
+1
c1
c2
c3
New representation
for input.
Use [c1, c3, c3] as representation to feed to learning algorithm.
Deep Belief Network
DBN is algorithm for learning a feature hierarchy.
Building Block: 2-layer graphical model (Restricted Boltzmann
Machine).
Can then learn additional layers one at a time.
Schematic overview of
a deep belief net.
Deep Belief Network (2)
Input [x1, x2, x3, x4]
Layer 2. [a1, a2, a3]
Layer 3. [b1, b2, b3]
Similar to a sparse auto-encoder in many ways.
Stack RBMs on top of each other to get DBN.
January 5, 2017 34
Convolutional DBN for Audio
Spectrogram
Detection units
Max pooling unit
January 5, 2017 35
Convolutional DBN for Audio (2)
Spectrogram
January 5, 2017 36
Convolutional DBN for Images
January 5, 2017 37
Going Deep
Pixels
Object Models
[Honglak Lee]
Training Set: Aligned
images of faces.
January 5, 2017 38
Edges
Object Parts
(combination of edges)
Applications
o Computer Vision: Object
Detection & Recognition
o Speech Recognition
o Speaker Identification
o Web Searches
o Text Classification - Sentiment
Analysis
o Translations
o Miscellaneous
o Fine-grained Classification
o Generalization
o Generating Image Captions from
Pixels
o …
January 5, 2017 39
Applications (2)
January 5, 2017 40
Speech Recognition on Android
January 5, 2017 41
Impact on Speech Recognition
January 5, 2017 42
Text Classifications
January 5, 2017 43
Results for IMDB Sentiment Classification
(long paragraphs)
Translation
o Google Translate:
o As Reuters noted for the first time in July, the seating configuration is exactly
what fuels the battle between the latest devices.
o Neural LSTM Model:
o As Reuters reported for the first time in July, the configuration of seats is
exactly what drives the battle between the latest aircraft.
o Human Translation:
o As Reuters first reported in July, seat layout is exactly what drives the battle
between the latest jets.
January 5, 2017 44
Good Fine-grained Classification
January 5, 2017 45
Good Generalization
January 5, 2017 46
Sensible Errors
January 5, 2017 47
Generating Image Captions from Pixels
January 5, 2017 48
Work by Oriol
Vinyals et al.
Generating Image Captions from Pixels(2)
January 5, 2017 49
Generating Image Captions from Pixels(3)
January 5, 2017 50
Generating Image Captions from Pixels(4)
January 5, 2017 51
Conclusion
Deep Neural Networks are very effective for wide range of tasks
o By using parallelism, we can quickly train very large and effective deep neural
models on very large datasets
o Automatically build high-level representations to solve desired tasks
o By using embedding, can work with sparse data
o Effective in many domains: speech, vision, language modeling, user prediction,
language understanding, translation, advertising, …
January 5, 2017 52
An important tool in building Intelligent Systems !
Thank You !
Q/A ?
January 5, 2017 53
Recommendations
o Le, Ranzato, Monga, Devin, Chen, Corrado, Dean, & Ng. Building High-Level Features Using Large
Scale Unsupervised Learning, ICML 2012.
o Dean, Corrado, et al. , Large Scale Distributed Deep Networks, NIPS 2012.
o Mikolov, Chen, Corrado and Dean. Efficient Estimation of Word Representations in Vector Space,
http://arxiv.org/abs/1301.3781.
o Distributed Representations of Sentences and Documents, by Quoc Le and Tomas Mikolov, ICML
2014, http://arxiv.org/abs/1405.4053
o Vanhoucke, Devin and Heigold. Deep Neural Networks for Acoustic Modeling, ICASSP 2013.
o Sequence to Sequence Learning with Neural Networks, Ilya Sutskever, Oriol Vinyals, and Quoc Le.
http://arxiv.org/abs/1409.3215. To appear in NIPS, 2014.
o http://research.google.com/papers
o http://research.google.com/people/jeff
January 5, 2017 54

Más contenido relacionado

La actualidad más candente

Machine Learning vs. Deep Learning
Machine Learning vs. Deep LearningMachine Learning vs. Deep Learning
Machine Learning vs. Deep LearningBelatrix Software
 
Deep learning - A Visual Introduction
Deep learning - A Visual IntroductionDeep learning - A Visual Introduction
Deep learning - A Visual IntroductionLukas Masuch
 
Deep Learning - A Literature survey
Deep Learning - A Literature surveyDeep Learning - A Literature survey
Deep Learning - A Literature surveyAkshay Hegde
 
Generative Adversarial Networks
Generative Adversarial NetworksGenerative Adversarial Networks
Generative Adversarial NetworksMustafa Yagmur
 
Machine Learning vs Deep Learning vs Artificial Intelligence | ML vs DL vs AI...
Machine Learning vs Deep Learning vs Artificial Intelligence | ML vs DL vs AI...Machine Learning vs Deep Learning vs Artificial Intelligence | ML vs DL vs AI...
Machine Learning vs Deep Learning vs Artificial Intelligence | ML vs DL vs AI...Simplilearn
 
GAN - Theory and Applications
GAN - Theory and ApplicationsGAN - Theory and Applications
GAN - Theory and ApplicationsEmanuele Ghelfi
 
Introduction to Deep learning
Introduction to Deep learningIntroduction to Deep learning
Introduction to Deep learningleopauly
 
Language modelling and its use cases
Language modelling and its use casesLanguage modelling and its use cases
Language modelling and its use casesKhrystyna Skopyk
 
What Is Deep Learning? | Introduction to Deep Learning | Deep Learning Tutori...
What Is Deep Learning? | Introduction to Deep Learning | Deep Learning Tutori...What Is Deep Learning? | Introduction to Deep Learning | Deep Learning Tutori...
What Is Deep Learning? | Introduction to Deep Learning | Deep Learning Tutori...Simplilearn
 
Generative adversarial networks
Generative adversarial networksGenerative adversarial networks
Generative adversarial networks남주 김
 
1시간만에 GAN(Generative Adversarial Network) 완전 정복하기
1시간만에 GAN(Generative Adversarial Network) 완전 정복하기1시간만에 GAN(Generative Adversarial Network) 완전 정복하기
1시간만에 GAN(Generative Adversarial Network) 완전 정복하기NAVER Engineering
 
GAN in medical imaging
GAN in medical imagingGAN in medical imaging
GAN in medical imagingCheng-Bin Jin
 
Machine Learning and Real-World Applications
Machine Learning and Real-World ApplicationsMachine Learning and Real-World Applications
Machine Learning and Real-World ApplicationsMachinePulse
 
Machine Learning
Machine LearningMachine Learning
Machine LearningKumar P
 
Natural Language Processing (NLP) - Introduction
Natural Language Processing (NLP) - IntroductionNatural Language Processing (NLP) - Introduction
Natural Language Processing (NLP) - IntroductionAritra Mukherjee
 
An Introduction to Deep Learning
An Introduction to Deep LearningAn Introduction to Deep Learning
An Introduction to Deep LearningPoo Kuan Hoong
 

La actualidad más candente (20)

Machine Learning vs. Deep Learning
Machine Learning vs. Deep LearningMachine Learning vs. Deep Learning
Machine Learning vs. Deep Learning
 
Deep learning - A Visual Introduction
Deep learning - A Visual IntroductionDeep learning - A Visual Introduction
Deep learning - A Visual Introduction
 
Transfer Learning
Transfer LearningTransfer Learning
Transfer Learning
 
Deep Learning - A Literature survey
Deep Learning - A Literature surveyDeep Learning - A Literature survey
Deep Learning - A Literature survey
 
Generative Adversarial Networks
Generative Adversarial NetworksGenerative Adversarial Networks
Generative Adversarial Networks
 
Machine learning
Machine learningMachine learning
Machine learning
 
Machine Learning vs Deep Learning vs Artificial Intelligence | ML vs DL vs AI...
Machine Learning vs Deep Learning vs Artificial Intelligence | ML vs DL vs AI...Machine Learning vs Deep Learning vs Artificial Intelligence | ML vs DL vs AI...
Machine Learning vs Deep Learning vs Artificial Intelligence | ML vs DL vs AI...
 
GAN - Theory and Applications
GAN - Theory and ApplicationsGAN - Theory and Applications
GAN - Theory and Applications
 
1.Introduction to deep learning
1.Introduction to deep learning1.Introduction to deep learning
1.Introduction to deep learning
 
Introduction to Deep learning
Introduction to Deep learningIntroduction to Deep learning
Introduction to Deep learning
 
Language modelling and its use cases
Language modelling and its use casesLanguage modelling and its use cases
Language modelling and its use cases
 
What Is Deep Learning? | Introduction to Deep Learning | Deep Learning Tutori...
What Is Deep Learning? | Introduction to Deep Learning | Deep Learning Tutori...What Is Deep Learning? | Introduction to Deep Learning | Deep Learning Tutori...
What Is Deep Learning? | Introduction to Deep Learning | Deep Learning Tutori...
 
Generative adversarial networks
Generative adversarial networksGenerative adversarial networks
Generative adversarial networks
 
1시간만에 GAN(Generative Adversarial Network) 완전 정복하기
1시간만에 GAN(Generative Adversarial Network) 완전 정복하기1시간만에 GAN(Generative Adversarial Network) 완전 정복하기
1시간만에 GAN(Generative Adversarial Network) 완전 정복하기
 
Tutorial on Deep Learning
Tutorial on Deep LearningTutorial on Deep Learning
Tutorial on Deep Learning
 
GAN in medical imaging
GAN in medical imagingGAN in medical imaging
GAN in medical imaging
 
Machine Learning and Real-World Applications
Machine Learning and Real-World ApplicationsMachine Learning and Real-World Applications
Machine Learning and Real-World Applications
 
Machine Learning
Machine LearningMachine Learning
Machine Learning
 
Natural Language Processing (NLP) - Introduction
Natural Language Processing (NLP) - IntroductionNatural Language Processing (NLP) - Introduction
Natural Language Processing (NLP) - Introduction
 
An Introduction to Deep Learning
An Introduction to Deep LearningAn Introduction to Deep Learning
An Introduction to Deep Learning
 

Destacado

Deep belief networks for spam filtering
Deep belief networks for spam filteringDeep belief networks for spam filtering
Deep belief networks for spam filteringSOYEON KIM
 
Data Science: A Mindset for Productivity
Data Science: A Mindset for ProductivityData Science: A Mindset for Productivity
Data Science: A Mindset for ProductivityDaniel Tunkelang
 
Generating Musical Notes and Transcription using Deep Learning
Generating Musical Notes and Transcription using Deep LearningGenerating Musical Notes and Transcription using Deep Learning
Generating Musical Notes and Transcription using Deep LearningVarad Meru
 
DDoS Attacks in 2017: Beyond Packet Filtering
DDoS Attacks in 2017: Beyond Packet FilteringDDoS Attacks in 2017: Beyond Packet Filtering
DDoS Attacks in 2017: Beyond Packet FilteringQrator Labs
 
Audit Denial of Service (ddos)
Audit Denial of Service (ddos)Audit Denial of Service (ddos)
Audit Denial of Service (ddos)Phonesec
 
10 Most Common DDo S Attacks
10 Most Common DDo S Attacks10 Most Common DDo S Attacks
10 Most Common DDo S AttacksIntruGuard
 
Denial of Service Attacks (DoS/DDoS)
Denial of Service Attacks (DoS/DDoS)Denial of Service Attacks (DoS/DDoS)
Denial of Service Attacks (DoS/DDoS)Gaurav Sharma
 
Whole Foods Strategic Audit
Whole Foods Strategic AuditWhole Foods Strategic Audit
Whole Foods Strategic Auditavanrivers
 
CEH - Module 10 : Denial of Service
CEH - Module 10 : Denial of ServiceCEH - Module 10 : Denial of Service
CEH - Module 10 : Denial of ServiceAvirot Mitamura
 
Deep Belief nets
Deep Belief netsDeep Belief nets
Deep Belief netsbutest
 
DDoS Attack Detection & Mitigation in SDN
DDoS Attack Detection & Mitigation in SDNDDoS Attack Detection & Mitigation in SDN
DDoS Attack Detection & Mitigation in SDNChao Chen
 
Deep Learning for NLP (without Magic) - Richard Socher and Christopher Manning
Deep Learning for NLP (without Magic) - Richard Socher and Christopher ManningDeep Learning for NLP (without Magic) - Richard Socher and Christopher Manning
Deep Learning for NLP (without Magic) - Richard Socher and Christopher ManningBigDataCloud
 
05 02 surveillance et analyse de traffic tcpip
05 02 surveillance et analyse de traffic tcpip05 02 surveillance et analyse de traffic tcpip
05 02 surveillance et analyse de traffic tcpipNoël
 
Firewalls
FirewallsFirewalls
Firewallsc0r3war
 
Attaques DDoS par Bruno Tréguier
Attaques DDoS par Bruno TréguierAttaques DDoS par Bruno Tréguier
Attaques DDoS par Bruno TréguierAFEIT
 
La détection d'intrusions est-elle morte en 2003 ? (Éric Gingras)
La détection d'intrusions est-elle morte en 2003 ? (Éric Gingras)La détection d'intrusions est-elle morte en 2003 ? (Éric Gingras)
La détection d'intrusions est-elle morte en 2003 ? (Éric Gingras)Hackfest Communication
 

Destacado (20)

Deep belief networks for spam filtering
Deep belief networks for spam filteringDeep belief networks for spam filtering
Deep belief networks for spam filtering
 
Data Science: A Mindset for Productivity
Data Science: A Mindset for ProductivityData Science: A Mindset for Productivity
Data Science: A Mindset for Productivity
 
Generating Musical Notes and Transcription using Deep Learning
Generating Musical Notes and Transcription using Deep LearningGenerating Musical Notes and Transcription using Deep Learning
Generating Musical Notes and Transcription using Deep Learning
 
DDoS Attacks in 2017: Beyond Packet Filtering
DDoS Attacks in 2017: Beyond Packet FilteringDDoS Attacks in 2017: Beyond Packet Filtering
DDoS Attacks in 2017: Beyond Packet Filtering
 
DDoS attacks
DDoS attacksDDoS attacks
DDoS attacks
 
Audit Denial of Service (ddos)
Audit Denial of Service (ddos)Audit Denial of Service (ddos)
Audit Denial of Service (ddos)
 
10 Most Common DDo S Attacks
10 Most Common DDo S Attacks10 Most Common DDo S Attacks
10 Most Common DDo S Attacks
 
Denial of Service Attacks (DoS/DDoS)
Denial of Service Attacks (DoS/DDoS)Denial of Service Attacks (DoS/DDoS)
Denial of Service Attacks (DoS/DDoS)
 
D do s
D do sD do s
D do s
 
Whole Foods Strategic Audit
Whole Foods Strategic AuditWhole Foods Strategic Audit
Whole Foods Strategic Audit
 
CEH - Module 10 : Denial of Service
CEH - Module 10 : Denial of ServiceCEH - Module 10 : Denial of Service
CEH - Module 10 : Denial of Service
 
Deep Belief nets
Deep Belief netsDeep Belief nets
Deep Belief nets
 
DDoS Attack Detection & Mitigation in SDN
DDoS Attack Detection & Mitigation in SDNDDoS Attack Detection & Mitigation in SDN
DDoS Attack Detection & Mitigation in SDN
 
Snort IDS/IPS Basics
Snort IDS/IPS BasicsSnort IDS/IPS Basics
Snort IDS/IPS Basics
 
Deep Learning for NLP (without Magic) - Richard Socher and Christopher Manning
Deep Learning for NLP (without Magic) - Richard Socher and Christopher ManningDeep Learning for NLP (without Magic) - Richard Socher and Christopher Manning
Deep Learning for NLP (without Magic) - Richard Socher and Christopher Manning
 
05 02 surveillance et analyse de traffic tcpip
05 02 surveillance et analyse de traffic tcpip05 02 surveillance et analyse de traffic tcpip
05 02 surveillance et analyse de traffic tcpip
 
Firewalls
FirewallsFirewalls
Firewalls
 
Attaques DDoS par Bruno Tréguier
Attaques DDoS par Bruno TréguierAttaques DDoS par Bruno Tréguier
Attaques DDoS par Bruno Tréguier
 
Prés kais
Prés kaisPrés kais
Prés kais
 
La détection d'intrusions est-elle morte en 2003 ? (Éric Gingras)
La détection d'intrusions est-elle morte en 2003 ? (Éric Gingras)La détection d'intrusions est-elle morte en 2003 ? (Éric Gingras)
La détection d'intrusions est-elle morte en 2003 ? (Éric Gingras)
 

Similar a Deep Learning for Artificial Intelligence (AI)

Slides galvin-widjaja
Slides galvin-widjajaSlides galvin-widjaja
Slides galvin-widjajaCodePolitan
 
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
 
Deep Learning, an interactive introduction for NLP-ers
Deep Learning, an interactive introduction for NLP-ersDeep Learning, an interactive introduction for NLP-ers
Deep Learning, an interactive introduction for NLP-ersRoelof Pieters
 
Week1- Introduction.pptx
Week1- Introduction.pptxWeek1- Introduction.pptx
Week1- Introduction.pptxfahmi324663
 
Deep Learning & NLP: Graphs to the Rescue!
Deep Learning & NLP: Graphs to the Rescue!Deep Learning & NLP: Graphs to the Rescue!
Deep Learning & NLP: Graphs to the Rescue!Roelof Pieters
 
The State of ML for iOS: On the Advent of WWDC 2018 🕯
The State of ML for iOS: On the Advent of WWDC 2018 🕯The State of ML for iOS: On the Advent of WWDC 2018 🕯
The State of ML for iOS: On the Advent of WWDC 2018 🕯Meghan Kane
 
De cero a Machine Learning: un camino sencillo para llegar muy lejos
De cero a Machine Learning: un camino sencillo para llegar muy lejos De cero a Machine Learning: un camino sencillo para llegar muy lejos
De cero a Machine Learning: un camino sencillo para llegar muy lejos Emergya
 
Artificial_intelligence.pptx
Artificial_intelligence.pptxArtificial_intelligence.pptx
Artificial_intelligence.pptxjohn6938
 
Bridging the gap between AI and UI - DSI Vienna - full version
Bridging the gap between AI and UI - DSI Vienna - full versionBridging the gap between AI and UI - DSI Vienna - full version
Bridging the gap between AI and UI - DSI Vienna - full versionLiad Magen
 
Deep learning: challenges and applications
Deep learning: challenges and  applicationsDeep learning: challenges and  applications
Deep learning: challenges and applicationsAboul Ella Hassanien
 
Breaking Through The Challenges of Scalable Deep Learning for Video Analytics
Breaking Through The Challenges of Scalable Deep Learning for Video AnalyticsBreaking Through The Challenges of Scalable Deep Learning for Video Analytics
Breaking Through The Challenges of Scalable Deep Learning for Video AnalyticsJason Anderson
 
Introduction to neural networks and Keras
Introduction to neural networks and KerasIntroduction to neural networks and Keras
Introduction to neural networks and KerasJie He
 
Deep Learning, Where Are You Going?
Deep Learning, Where Are You Going?Deep Learning, Where Are You Going?
Deep Learning, Where Are You Going?NAVER Engineering
 
Visual concept learning
Visual concept learningVisual concept learning
Visual concept learningVaibhav Singh
 
Interactive Video Search: Where is the User in the Age of Deep Learning?
Interactive Video Search: Where is the User in the Age of Deep Learning?Interactive Video Search: Where is the User in the Age of Deep Learning?
Interactive Video Search: Where is the User in the Age of Deep Learning?klschoef
 
How Will AI Change the Role of the Data Scientist?
How Will AI Change the Role of the Data Scientist?How Will AI Change the Role of the Data Scientist?
How Will AI Change the Role of the Data Scientist?Hugo Gävert
 
Distributed Models Over Distributed Data with MLflow, Pyspark, and Pandas
Distributed Models Over Distributed Data with MLflow, Pyspark, and PandasDistributed Models Over Distributed Data with MLflow, Pyspark, and Pandas
Distributed Models Over Distributed Data with MLflow, Pyspark, and PandasDatabricks
 
A few questions about large scale machine learning
A few questions about large scale machine learningA few questions about large scale machine learning
A few questions about large scale machine learningTheodoros Vasiloudis
 
Generation of Synthetic Referring Expressions for Object Segmentation in Videos
Generation of Synthetic Referring Expressions for Object Segmentation in VideosGeneration of Synthetic Referring Expressions for Object Segmentation in Videos
Generation of Synthetic Referring Expressions for Object Segmentation in VideosUniversitat Politècnica de Catalunya
 
Big Data: the weakest link
Big Data: the weakest linkBig Data: the weakest link
Big Data: the weakest linkCS, NcState
 

Similar a Deep Learning for Artificial Intelligence (AI) (20)

Slides galvin-widjaja
Slides galvin-widjajaSlides galvin-widjaja
Slides galvin-widjaja
 
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
 
Deep Learning, an interactive introduction for NLP-ers
Deep Learning, an interactive introduction for NLP-ersDeep Learning, an interactive introduction for NLP-ers
Deep Learning, an interactive introduction for NLP-ers
 
Week1- Introduction.pptx
Week1- Introduction.pptxWeek1- Introduction.pptx
Week1- Introduction.pptx
 
Deep Learning & NLP: Graphs to the Rescue!
Deep Learning & NLP: Graphs to the Rescue!Deep Learning & NLP: Graphs to the Rescue!
Deep Learning & NLP: Graphs to the Rescue!
 
The State of ML for iOS: On the Advent of WWDC 2018 🕯
The State of ML for iOS: On the Advent of WWDC 2018 🕯The State of ML for iOS: On the Advent of WWDC 2018 🕯
The State of ML for iOS: On the Advent of WWDC 2018 🕯
 
De cero a Machine Learning: un camino sencillo para llegar muy lejos
De cero a Machine Learning: un camino sencillo para llegar muy lejos De cero a Machine Learning: un camino sencillo para llegar muy lejos
De cero a Machine Learning: un camino sencillo para llegar muy lejos
 
Artificial_intelligence.pptx
Artificial_intelligence.pptxArtificial_intelligence.pptx
Artificial_intelligence.pptx
 
Bridging the gap between AI and UI - DSI Vienna - full version
Bridging the gap between AI and UI - DSI Vienna - full versionBridging the gap between AI and UI - DSI Vienna - full version
Bridging the gap between AI and UI - DSI Vienna - full version
 
Deep learning: challenges and applications
Deep learning: challenges and  applicationsDeep learning: challenges and  applications
Deep learning: challenges and applications
 
Breaking Through The Challenges of Scalable Deep Learning for Video Analytics
Breaking Through The Challenges of Scalable Deep Learning for Video AnalyticsBreaking Through The Challenges of Scalable Deep Learning for Video Analytics
Breaking Through The Challenges of Scalable Deep Learning for Video Analytics
 
Introduction to neural networks and Keras
Introduction to neural networks and KerasIntroduction to neural networks and Keras
Introduction to neural networks and Keras
 
Deep Learning, Where Are You Going?
Deep Learning, Where Are You Going?Deep Learning, Where Are You Going?
Deep Learning, Where Are You Going?
 
Visual concept learning
Visual concept learningVisual concept learning
Visual concept learning
 
Interactive Video Search: Where is the User in the Age of Deep Learning?
Interactive Video Search: Where is the User in the Age of Deep Learning?Interactive Video Search: Where is the User in the Age of Deep Learning?
Interactive Video Search: Where is the User in the Age of Deep Learning?
 
How Will AI Change the Role of the Data Scientist?
How Will AI Change the Role of the Data Scientist?How Will AI Change the Role of the Data Scientist?
How Will AI Change the Role of the Data Scientist?
 
Distributed Models Over Distributed Data with MLflow, Pyspark, and Pandas
Distributed Models Over Distributed Data with MLflow, Pyspark, and PandasDistributed Models Over Distributed Data with MLflow, Pyspark, and Pandas
Distributed Models Over Distributed Data with MLflow, Pyspark, and Pandas
 
A few questions about large scale machine learning
A few questions about large scale machine learningA few questions about large scale machine learning
A few questions about large scale machine learning
 
Generation of Synthetic Referring Expressions for Object Segmentation in Videos
Generation of Synthetic Referring Expressions for Object Segmentation in VideosGeneration of Synthetic Referring Expressions for Object Segmentation in Videos
Generation of Synthetic Referring Expressions for Object Segmentation in Videos
 
Big Data: the weakest link
Big Data: the weakest linkBig Data: the weakest link
Big Data: the weakest link
 

Más de Er. Shiva K. Shrestha

Más de Er. Shiva K. Shrestha (7)

Workshop on Classroom and Meet - Er. Shiva K. Shrestha
Workshop on Classroom and Meet - Er. Shiva K. ShresthaWorkshop on Classroom and Meet - Er. Shiva K. Shrestha
Workshop on Classroom and Meet - Er. Shiva K. Shrestha
 
Numerical Computing
Numerical Computing Numerical Computing
Numerical Computing
 
DDoS - Distributed Denial of Service
DDoS - Distributed Denial of ServiceDDoS - Distributed Denial of Service
DDoS - Distributed Denial of Service
 
Executing Joins Dynamically in DDBS Query Optimizer
Executing Joins Dynamically in DDBS Query OptimizerExecuting Joins Dynamically in DDBS Query Optimizer
Executing Joins Dynamically in DDBS Query Optimizer
 
Comparison of Amoeba, Mach & Chorus: DOS
Comparison of Amoeba, Mach & Chorus: DOSComparison of Amoeba, Mach & Chorus: DOS
Comparison of Amoeba, Mach & Chorus: DOS
 
Software Configuration Management (SCM)
Software Configuration Management (SCM)Software Configuration Management (SCM)
Software Configuration Management (SCM)
 
Mongo DB
Mongo DBMongo DB
Mongo DB
 

Último

🐬 The future of MySQL is Postgres 🐘
🐬  The future of MySQL is Postgres   🐘🐬  The future of MySQL is Postgres   🐘
🐬 The future of MySQL is Postgres 🐘RTylerCroy
 
Slack Application Development 101 Slides
Slack Application Development 101 SlidesSlack Application Development 101 Slides
Slack Application Development 101 Slidespraypatel2
 
IAC 2024 - IA Fast Track to Search Focused AI Solutions
IAC 2024 - IA Fast Track to Search Focused AI SolutionsIAC 2024 - IA Fast Track to Search Focused AI Solutions
IAC 2024 - IA Fast Track to Search Focused AI SolutionsEnterprise Knowledge
 
From Event to Action: Accelerate Your Decision Making with Real-Time Automation
From Event to Action: Accelerate Your Decision Making with Real-Time AutomationFrom Event to Action: Accelerate Your Decision Making with Real-Time Automation
From Event to Action: Accelerate Your Decision Making with Real-Time AutomationSafe Software
 
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
 
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
 
A Domino Admins Adventures (Engage 2024)
A Domino Admins Adventures (Engage 2024)A Domino Admins Adventures (Engage 2024)
A Domino Admins Adventures (Engage 2024)Gabriella Davis
 
Workshop - Best of Both Worlds_ Combine KG and Vector search for enhanced R...
Workshop - Best of Both Worlds_ Combine  KG and Vector search for  enhanced R...Workshop - Best of Both Worlds_ Combine  KG and Vector search for  enhanced R...
Workshop - Best of Both Worlds_ Combine KG and Vector search for enhanced R...Neo4j
 
2024: Domino Containers - The Next Step. News from the Domino Container commu...
2024: Domino Containers - The Next Step. News from the Domino Container commu...2024: Domino Containers - The Next Step. News from the Domino Container commu...
2024: Domino Containers - The Next Step. News from the Domino Container commu...Martijn de Jong
 
Breaking the Kubernetes Kill Chain: Host Path Mount
Breaking the Kubernetes Kill Chain: Host Path MountBreaking the Kubernetes Kill Chain: Host Path Mount
Breaking the Kubernetes Kill Chain: Host Path MountPuma Security, LLC
 
TrustArc Webinar - Stay Ahead of US State Data Privacy Law Developments
TrustArc Webinar - Stay Ahead of US State Data Privacy Law DevelopmentsTrustArc Webinar - Stay Ahead of US State Data Privacy Law Developments
TrustArc Webinar - Stay Ahead of US State Data Privacy Law DevelopmentsTrustArc
 
The Role of Taxonomy and Ontology in Semantic Layers - Heather Hedden.pdf
The Role of Taxonomy and Ontology in Semantic Layers - Heather Hedden.pdfThe Role of Taxonomy and Ontology in Semantic Layers - Heather Hedden.pdf
The Role of Taxonomy and Ontology in Semantic Layers - Heather Hedden.pdfEnterprise Knowledge
 
Factors to Consider When Choosing Accounts Payable Services Providers.pptx
Factors to Consider When Choosing Accounts Payable Services Providers.pptxFactors to Consider When Choosing Accounts Payable Services Providers.pptx
Factors to Consider When Choosing Accounts Payable Services Providers.pptxKatpro Technologies
 
Injustice - Developers Among Us (SciFiDevCon 2024)
Injustice - Developers Among Us (SciFiDevCon 2024)Injustice - Developers Among Us (SciFiDevCon 2024)
Injustice - Developers Among Us (SciFiDevCon 2024)Allon Mureinik
 
[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
 
Presentation on how to chat with PDF using ChatGPT code interpreter
Presentation on how to chat with PDF using ChatGPT code interpreterPresentation on how to chat with PDF using ChatGPT code interpreter
Presentation on how to chat with PDF using ChatGPT code interpreternaman860154
 
CNv6 Instructor Chapter 6 Quality of Service
CNv6 Instructor Chapter 6 Quality of ServiceCNv6 Instructor Chapter 6 Quality of Service
CNv6 Instructor Chapter 6 Quality of Servicegiselly40
 
Raspberry Pi 5: Challenges and Solutions in Bringing up an OpenGL/Vulkan Driv...
Raspberry Pi 5: Challenges and Solutions in Bringing up an OpenGL/Vulkan Driv...Raspberry Pi 5: Challenges and Solutions in Bringing up an OpenGL/Vulkan Driv...
Raspberry Pi 5: Challenges and Solutions in Bringing up an OpenGL/Vulkan Driv...Igalia
 
Unblocking The Main Thread Solving ANRs and Frozen Frames
Unblocking The Main Thread Solving ANRs and Frozen FramesUnblocking The Main Thread Solving ANRs and Frozen Frames
Unblocking The Main Thread Solving ANRs and Frozen FramesSinan KOZAK
 

Último (20)

🐬 The future of MySQL is Postgres 🐘
🐬  The future of MySQL is Postgres   🐘🐬  The future of MySQL is Postgres   🐘
🐬 The future of MySQL is Postgres 🐘
 
Slack Application Development 101 Slides
Slack Application Development 101 SlidesSlack Application Development 101 Slides
Slack Application Development 101 Slides
 
IAC 2024 - IA Fast Track to Search Focused AI Solutions
IAC 2024 - IA Fast Track to Search Focused AI SolutionsIAC 2024 - IA Fast Track to Search Focused AI Solutions
IAC 2024 - IA Fast Track to Search Focused AI Solutions
 
From Event to Action: Accelerate Your Decision Making with Real-Time Automation
From Event to Action: Accelerate Your Decision Making with Real-Time AutomationFrom Event to Action: Accelerate Your Decision Making with Real-Time Automation
From Event to Action: Accelerate Your Decision Making with Real-Time Automation
 
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...
 
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
 
A Domino Admins Adventures (Engage 2024)
A Domino Admins Adventures (Engage 2024)A Domino Admins Adventures (Engage 2024)
A Domino Admins Adventures (Engage 2024)
 
Workshop - Best of Both Worlds_ Combine KG and Vector search for enhanced R...
Workshop - Best of Both Worlds_ Combine  KG and Vector search for  enhanced R...Workshop - Best of Both Worlds_ Combine  KG and Vector search for  enhanced R...
Workshop - Best of Both Worlds_ Combine KG and Vector search for enhanced R...
 
2024: Domino Containers - The Next Step. News from the Domino Container commu...
2024: Domino Containers - The Next Step. News from the Domino Container commu...2024: Domino Containers - The Next Step. News from the Domino Container commu...
2024: Domino Containers - The Next Step. News from the Domino Container commu...
 
Breaking the Kubernetes Kill Chain: Host Path Mount
Breaking the Kubernetes Kill Chain: Host Path MountBreaking the Kubernetes Kill Chain: Host Path Mount
Breaking the Kubernetes Kill Chain: Host Path Mount
 
TrustArc Webinar - Stay Ahead of US State Data Privacy Law Developments
TrustArc Webinar - Stay Ahead of US State Data Privacy Law DevelopmentsTrustArc Webinar - Stay Ahead of US State Data Privacy Law Developments
TrustArc Webinar - Stay Ahead of US State Data Privacy Law Developments
 
The Role of Taxonomy and Ontology in Semantic Layers - Heather Hedden.pdf
The Role of Taxonomy and Ontology in Semantic Layers - Heather Hedden.pdfThe Role of Taxonomy and Ontology in Semantic Layers - Heather Hedden.pdf
The Role of Taxonomy and Ontology in Semantic Layers - Heather Hedden.pdf
 
Factors to Consider When Choosing Accounts Payable Services Providers.pptx
Factors to Consider When Choosing Accounts Payable Services Providers.pptxFactors to Consider When Choosing Accounts Payable Services Providers.pptx
Factors to Consider When Choosing Accounts Payable Services Providers.pptx
 
Injustice - Developers Among Us (SciFiDevCon 2024)
Injustice - Developers Among Us (SciFiDevCon 2024)Injustice - Developers Among Us (SciFiDevCon 2024)
Injustice - Developers Among Us (SciFiDevCon 2024)
 
[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
 
Presentation on how to chat with PDF using ChatGPT code interpreter
Presentation on how to chat with PDF using ChatGPT code interpreterPresentation on how to chat with PDF using ChatGPT code interpreter
Presentation on how to chat with PDF using ChatGPT code interpreter
 
CNv6 Instructor Chapter 6 Quality of Service
CNv6 Instructor Chapter 6 Quality of ServiceCNv6 Instructor Chapter 6 Quality of Service
CNv6 Instructor Chapter 6 Quality of Service
 
Raspberry Pi 5: Challenges and Solutions in Bringing up an OpenGL/Vulkan Driv...
Raspberry Pi 5: Challenges and Solutions in Bringing up an OpenGL/Vulkan Driv...Raspberry Pi 5: Challenges and Solutions in Bringing up an OpenGL/Vulkan Driv...
Raspberry Pi 5: Challenges and Solutions in Bringing up an OpenGL/Vulkan Driv...
 
Unblocking The Main Thread Solving ANRs and Frozen Frames
Unblocking The Main Thread Solving ANRs and Frozen FramesUnblocking The Main Thread Solving ANRs and Frozen Frames
Unblocking The Main Thread Solving ANRs and Frozen Frames
 

Deep Learning for Artificial Intelligence (AI)

  • 1. January 5, 2017 1 Deep Learning Er. Shiva K. Shrestha, ME Computer, NCIT
  • 2. Slide Credit o Jeff Dean, Google, Large Scale Deep Learning o Andrew Ng, Deep Learning o Aditya Khosla & Joseph Lim, Visual Recognition through ML Competition January 5, 2017 2
  • 3. Structure ◦ General Questions of the World ◦ What is Deep Learning? ◦ Why Deep Learning? ◦ Deep Neural Network Architectures ◦ Deep Learning Applications ◦ Conclusions, Recommendations January 5, 2017 3
  • 4. How Can We Build More Intelligent Computer Systems? According to Jeff Dean, Google: o Need to perceive and understand the world o Basic speech and vision capabilities o Language understanding o User behavior prediction o … January 5, 2017 4
  • 5. How can we do this? According to Jeff Dean, Google: o Cannot write algorithms for each task we want to accomplish separately. o Need to write general algorithms that learn from observations o Can we build systems that: o Generate understanding from raw data o Solve difficult problems to improve products o Minimize software engineering effort January 5, 2017 5
  • 6. Plenty of Data o Text: trillions of words of English + other languages o Visual: billions of images and videos o Audio: thousands of hours of speech per day o User Activity: queries, result page clicks, map requests, etc. o Knowledge Graph: billions of labelled relation triples o … January 5, 2017 6
  • 8. What are these numbers? January 5, 2017 8
  • 9. What are all these words? January 5, 2017 9
  • 10. How about these words? January 5, 2017 10
  • 11. Textual Understanding “This movie should have NEVER been made. From the poorly done animation, to the beyond bad acting. I am not sure at what point the people behind this movie said "Ok, looks good! Lets do it!" I was in awe of how truly horrid this movie was.” January 5, 2017 11
  • 12. General Machine Learning Approaches o Learning by labeled example: Supervised Learning o e.g. An email spam detector o amazingly effective if you have lots of examples o Discovering patterns: Unsupervised Learning o e.g. data clustering o difficult in practice, but useful if you lack labeled examples o Feedback right/wrong: Reinforcement Learning o e.g. learning to play chess by winning or losing o works well in some domains, becoming more important January 5, 2017 12
  • 13. Machine Learning o For many of these problems, we have lots of data o gives computers the ability to learn without being explicitly programmed January 5, 2017 13 Approaches o Decision tree learning o Association rule learning o Artificial neural networks o Deep learning o Inductive logic programming o Support vector machines o Clustering o Bayesian networks Approaches … o Reinforcement learning o Representation learning o Similarity and metric learning o Sparse dictionary learning o Genetic algorithms o Rule-based machine learning o Learning classifier systems
  • 14. Typical Goal of Machine Learning Label: “Motorcycle” Suggest tags Image search … Speech recognition Music classification Speaker identification … Web search Anti-spam Machine translation … text audio images/video I/p O/p ML ML ML January 5, 2017 14
  • 15. Basic Idea of Deep Learning Is there some way to extract meaningful features from data even without knowing the task to be performed? Then, throw in some hierarchical ‘stuff’ to make it ‘deep’ January 5, 2017 15
  • 16. What is Deep Learning? o The modern reincarnation of ANNs from the 1980s and 90s. o A collection of simple trainable mathematical units, which collaborate to compute a complicated function. oCompatible with (3) General ML Approaches January 5, 2017 16
  • 17. What is Deep Learning? (2) o Loosely inspired by what (little) we know about the biological brain. o AKA: o Deep Structure Learning o Hierarchical Learning o Deep M/c Learning January 5, 2017 17
  • 18. Deep Learning Definitions Deep learning is characterized as a class of machine learning algorithms that o use a cascade of many layers of nonlinear processing units for feature extraction and transformation. o are based on the learning of multiple levels of features or representations of the data. o are part of the broader machine learning field of learning representations of data. o learn multiple levels of representations that correspond to different levels of abstraction; January 5, 2017 18
  • 19. DL - Why is this hard? You see this: But the camera sees this: January 5, 2017 19
  • 22. Pixel-based Representation (2) Input Motorbikes “Non”-Motorbikes Learning algorithm pixel 1 pixel2 pixel 1 pixel 2 Raw image January 5, 2017 22
  • 23. What We Want Input Motorbikes “Non”-Motorbikes Learning algorithm pixel 1 pixel2 Feature representation handlebars wheel E.g., Does it have Handlebars? Wheels? Handlebars Wheels Raw image Features January 5, 2017 23
  • 24. Some Feature Representations SIFT Spin image HoG RIFT Textons GLOH January 5, 2017 24
  • 25. Some Feature Representations (2) SIFT Spin image HoG RIFT Textons GLOH Coming up with features is often difficult, time- consuming, and requires expert knowledge. January 5, 2017 25
  • 26. The Brain: Potential Motivation for Deep Learning [Roe et al., 1992] Auditory Cortex learns to see! Auditory Cortex January 5, 2017 26
  • 27. The Brain adapts! [BrainPort; Welsh & Blasch, 1997; Nagel et al., 2005; Constantine-Paton & Law, 2009] Seeing with your Tongue Human Echolocation (Sonar) Haptic belt: Direction Sense Implanting a 3rd Eye January 5, 2017 27
  • 28. Feature Learning Problem Given a 14x14 image patch x, can represent it using 196 real numbers. Problem: Can we find a learn a better feature vector to represent this? 255 98 93 87 89 91 48 … January 5, 2017 28
  • 29. Why Deep Learning? Method Accuracy Hessian + ESURF [Williems et al 2008] 38% Harris3D + HOG/HOF [Laptev et al 2003, 2004] 45% Cuboids + HOG/HOF [Dollar et al 2005, Laptev 2004] 46% Hessian + HOG/HOF [Laptev 2004, Williems et al 2008] 46% Dense + HOG / HOF [Laptev 2004] 47% Cuboids + HOG3D [Klaser 2008, Dollar et al 2005] 46% Unsupervised Feature Learning (DL) 52% [Le, Zhou & Ng, 2011] Task: Video Activity Recognition January 5, 2017 29
  • 30. Deep Neural Network Architectures o GMDH: 1st DLN of 1965 o Convolutional NN o Neural history compressor o Recursive NN o Long short-term memory (LSTM) o Deep belief networks (DBN) o Convolutional deep belief networks o Large memory storage & retrieval NN o Deep Boltzmann machines o Stacked (de-noising) auto-encoders o Deep stacking networks o Tensor deep stacking networks o Spike-and-slab RBMs o Compound hierarchical-deep models o Deep coding networks o Deep Q-networks o Networks with separate memory structures January 5, 2017 30
  • 31. Neural Network (NN) x1 x2 x3 +1 +1 Layer 1 Layer 2 Layer 4+1 Layer 3 4 layer network with 2 output units: January 5, 2017 31
  • 32. Unsupervised Feature Learning with a NN x4 x5 x6 +1 x1 x2 x3 +1 a1 a2 a3 +1 b1 b2 b3 +1 c1 c2 c3 New representation for input. Use [c1, c3, c3] as representation to feed to learning algorithm.
  • 33. Deep Belief Network DBN is algorithm for learning a feature hierarchy. Building Block: 2-layer graphical model (Restricted Boltzmann Machine). Can then learn additional layers one at a time. Schematic overview of a deep belief net.
  • 34. Deep Belief Network (2) Input [x1, x2, x3, x4] Layer 2. [a1, a2, a3] Layer 3. [b1, b2, b3] Similar to a sparse auto-encoder in many ways. Stack RBMs on top of each other to get DBN. January 5, 2017 34
  • 35. Convolutional DBN for Audio Spectrogram Detection units Max pooling unit January 5, 2017 35
  • 36. Convolutional DBN for Audio (2) Spectrogram January 5, 2017 36
  • 37. Convolutional DBN for Images January 5, 2017 37
  • 38. Going Deep Pixels Object Models [Honglak Lee] Training Set: Aligned images of faces. January 5, 2017 38 Edges Object Parts (combination of edges)
  • 39. Applications o Computer Vision: Object Detection & Recognition o Speech Recognition o Speaker Identification o Web Searches o Text Classification - Sentiment Analysis o Translations o Miscellaneous o Fine-grained Classification o Generalization o Generating Image Captions from Pixels o … January 5, 2017 39
  • 41. Speech Recognition on Android January 5, 2017 41
  • 42. Impact on Speech Recognition January 5, 2017 42
  • 43. Text Classifications January 5, 2017 43 Results for IMDB Sentiment Classification (long paragraphs)
  • 44. Translation o Google Translate: o As Reuters noted for the first time in July, the seating configuration is exactly what fuels the battle between the latest devices. o Neural LSTM Model: o As Reuters reported for the first time in July, the configuration of seats is exactly what drives the battle between the latest aircraft. o Human Translation: o As Reuters first reported in July, seat layout is exactly what drives the battle between the latest jets. January 5, 2017 44
  • 48. Generating Image Captions from Pixels January 5, 2017 48 Work by Oriol Vinyals et al.
  • 49. Generating Image Captions from Pixels(2) January 5, 2017 49
  • 50. Generating Image Captions from Pixels(3) January 5, 2017 50
  • 51. Generating Image Captions from Pixels(4) January 5, 2017 51
  • 52. Conclusion Deep Neural Networks are very effective for wide range of tasks o By using parallelism, we can quickly train very large and effective deep neural models on very large datasets o Automatically build high-level representations to solve desired tasks o By using embedding, can work with sparse data o Effective in many domains: speech, vision, language modeling, user prediction, language understanding, translation, advertising, … January 5, 2017 52 An important tool in building Intelligent Systems !
  • 53. Thank You ! Q/A ? January 5, 2017 53
  • 54. Recommendations o Le, Ranzato, Monga, Devin, Chen, Corrado, Dean, & Ng. Building High-Level Features Using Large Scale Unsupervised Learning, ICML 2012. o Dean, Corrado, et al. , Large Scale Distributed Deep Networks, NIPS 2012. o Mikolov, Chen, Corrado and Dean. Efficient Estimation of Word Representations in Vector Space, http://arxiv.org/abs/1301.3781. o Distributed Representations of Sentences and Documents, by Quoc Le and Tomas Mikolov, ICML 2014, http://arxiv.org/abs/1405.4053 o Vanhoucke, Devin and Heigold. Deep Neural Networks for Acoustic Modeling, ICASSP 2013. o Sequence to Sequence Learning with Neural Networks, Ilya Sutskever, Oriol Vinyals, and Quoc Le. http://arxiv.org/abs/1409.3215. To appear in NIPS, 2014. o http://research.google.com/papers o http://research.google.com/people/jeff January 5, 2017 54