SlideShare uma empresa Scribd logo
1 de 75
Baixar para ler offline
@graphific
Roelof Pieters
Deep Learning:

a (non-techy) birds-eye
view
20	
  April	
  2015	
  
Stockholm
Deep Learning
Slides at:

http://www.slideshare.net/roelofp/deep-learning-a-birdseye-view
• Deals with “construction and study of systems that can
learn from data”
Refresher: Machine Learning ???
A computer program is said to learn from
experience (E) with respect to some class
of tasks (T) and performance measure
(P), if its performance at tasks in T, as
measured by P, improves with experience E
— T. Mitchell 1997
2
Improving some task T
based on experience E with
respect to performance
measure P.
Deep Learning = Machine Learning
Learning denotes changes in the system
that are adaptive in the sense that they
enable the system to do the same task
(or tasks drawn from a population of
similar tasks) more effectively the next
time.
— H. Simon 1983 

"Why Should Machines Learn?” in Mitchell 1997
— T. Mitchell 1997
3
Representation learning
Attempts to automatically learn
good features or
representations
Deep learning
Attempt to learn multiple levels
of representation of increasing
complexity/abstraction
Deep Learning: What?
4
Deep Learning ??
5
Machine Learning ??
Traditional Programming:
Data
Program
Output
6
Computer
Machine Learning ??
Traditional Programming:
Data
Program
Output
Data
Program
Output
Machine Learning:
7
(labels)
(“weights”/model)
Computer
Computer
Machine Learning ??
8
• Most machine learning
methods work well because of
human-designed/hand-
engineered features
(representations)
• machine learning ->
optimising weights to best
make a final prediction
Typical ML Regression
Deep Learning: Why?
Neural NetTypical ML Regression
Deep Learning: Why?
Machine ->Deep Learning ??
Machine ->Deep Learning ??
DEEP NET 

(DEEP LEARNING)
Biological Inspiration
14
Deep Learning: Why?
Deep Learning is everywhere…
Deep Learning in the News
(source: Google Trends)
19
(source: arXiv bookworm, Culturomics)
Scientific Articles:
Why Now?
• Inspired by the architectural depth of the brain,
researchers wanted for decades to train deep
multi-layer neural networks.
• No successful attempts were reported before 2006
…Exception: convolutional neural networks,
LeCun 1998
• SVM: Vapnik and his co-workers developed the
Support Vector Machine (1993) (shallow
architecture).
• Breakthrough in 2006!
25
Renewed Interest: 1990s
• Learning multiple layers
• “Back propagation”
• Can “theoretically” learn any function!
But…
• Very slow and inefficient
• SVMs, random forests, etc. SOTA
26
2006 Breakthrough
• More data
• Faster hardware: GPU’s, multi-core CPU’s
• Working ideas on how to train deep architectures
27
2006 Breakthrough
• More data
• Faster hardware: GPU’s, multi-core CPU’s
• Working ideas on how to train deep architectures
28
2006 Breakthrough
29
2006 Breakthrough
30
Growth of datasets
2006 Breakthrough
• More data
• Faster hardware: GPU’s, multi-core CPU’s
• Working ideas on how to train deep architectures
31
2006 Breakthrough
32
vs
Rise of Raw Computation Power
2006 Breakthrough
• More data
• Faster hardware: GPU’s, multi-core CPU’s
• Working ideas on how to train deep
architectures
34
2006 Breakthrough
Stacked Restricted Boltzman Machines* (RBM)
Hinton, G. E, Osindero, S., and Teh, Y. W. (2006).

A fast learning algorithm for deep belief nets.

Neural Computation, 18:1527-1554.
Stacked Autoencoders (AE)
Bengio, Y., Lamblin, P., Popovici, P., Larochelle, H. (2007).

Greedy Layer-Wise Training of Deep Networks,

Advances in Neural Information Processing Systems 19
* called Deep Belief Networks (DBN)
35
Deep Learning for the Win!
• 1.2M images with 1000 object categories
• AlexNet of uni Toronto: 15% error rate vs 26% for
2th placed (traditional CV)
Impact on Computer Vision
ImageNet Challenge 2012
Impact on Computer Vision
(from Clarifai)
Impact on Computer Vision
40
Classification results on ImageNet 2012
Team Year Place Error (top-5) Uses external
data
SuperVision 2012 - 16.4% no
SuperVision 2012 1st 15.3% ImageNet 22k
Clarifai 2013 - 11.7% no
Clarifai 2013 1st 11.2% ImageNet 22k
MSRA 2014 3rd 7.35% no
VGG 2014 2nd 7.32% no
GoogLeNet 2014 1st 6.67% no
Final Detection Results
Team Year Place mAP e x t e r n a l
data
ensemble c o n t e x t u a l
model
approach
UvA-Euvision 2013 1st 22.6% none
? yes F i s h e r
vectors
Deep Insight 2014 3rd 40.5% I L S V R C 1 2
Classification
+ Localization
3 models yes ConvNet
C U H K
DeepID-Net
2014 2nd 40.7% I L S V R C 1 2
Classification
+ Localization
? no ConvNet
GoogLeNet 2014 1st 43.9% I L S V R C 1 2
Classification
6 models no ConvNet
Detection results
source: Szegedy et al. Going deeper with convolutions (GoogLeNet ), ILSVRC2014, 19 Sep 2014
41source: Szegedy et al. Going deeper with convolutions (GoogLeNet ), ILSVRC2014, 19 Sep 2014
GoogLeNet
Convolution
Pooling
Softmax
Other
Winners of: 

Large Scale Visual Recognition Challenge 2014 

(ILSVRC2014)
19 September 2014
GoogLeNet
Convolution
Pooling
Softmax
Other
42source: Szegedy et al. Going deeper with convolutions (GoogLeNet ), ILSVRC2014, 19 Sep 2014
Inception
Width of inception modules ranges from 256 filters (in early modules) to 1024 in top inception
modules.
Can remove fully connected layers on top completely
Number of parameters is reduced to 5 million
256 480 480
512
512 512
832 832 1024
Computional cost is increased by
less than 2X compared to
Krizhevsky’s network. (<1.5Bn
operations/evaluation)
Impact on Computer Vision
Latest State of the Art:
Computer Vision: Current State of the Art
Impact on Audio Processing
45
First public Breakthrough with Deep Learning in 2010
Dahl et al. (2010)

Impact on Audio Processing
46
First public Breakthrough with Deep Learning in 2010
Dahl et al. (2010)

-33%! -32%!
Impact on Audio Processing
47
Speech Recognition
Impact on Audio Processing
48
TIMIT Speech Recognition
(from: Clarifai)
Impact on Audio Processing
C&W 2011
Impact on Natural Language Processing
Pos: Toutanova et al.

2003)
Ner: Ando & Zhang 

2005
C&W 2011
Impact on Natural Language Processing
Named Entity Recognition:
Deep Learning: Who’s to blame?
53
Deep Learning: Who’s to blame?
Deep Architectures can be representationally efficient
• Fewer computational units for same function
Deep Representations might allow for a hierarchy or
representation
• Allows non-local generalisation
• Comprehensibility
Multiple levels of latent variables allow combinatorial
sharing of statistical strength
54
Deep Learning: Why?
— Andrew Ng
“I’ve worked all my life in
Machine Learning, and I’ve
never seen one algorithm knock
over benchmarks like Deep
Learning”
Deep Learning: Why?
55
Biological Justification
Deep Learning = Brain “inspired”

Audio/Visual Cortex has multiple stages == Hierarchical
Different Levels of Abstraction
57
Hierarchical Learning
• Natural progression
from low level to high
level structure as seen
in natural complexity
Different Levels of Abstraction
Feature Representation
58
Hierarchical Learning
• Natural progression
from low level to high
level structure as seen
in natural complexity• Easier to monitor what
is being learnt and to
guide the machine to
better subspaces
Different Levels of Abstraction
Feature Representation
59
Hierarchical Learning
• Natural progression
from low level to high
level structure as seen
in natural complexity• Easier to monitor what
is being learnt and to
guide the machine to
better subspaces
• A good lower level
representation can be
used for many distinct
tasks
Different Levels of Abstraction
Feature Representation
60
Hierarchical Learning
• Natural progression
from low level to high
level structure as seen
in natural complexity• Easier to monitor what
is being learnt and to
guide the machine to
better subspaces
• A good lower level
representation can be
used for many distinct
tasks
Different Levels of Abstraction
Feature Representation
61
Different Levels of Abstraction
Classic Deep Architecture
Input layer
Hidden layers
Output layer
Modern Deep Architecture
Input layer
Hidden layers
Output layer
movie time:
http://www.cs.toronto.edu/~hinton/adi/index.htm
Hierarchies
Efficient
Generalization
Distributed
Sharing
Unsupervised*
Black Box
Training Time
Major PWNAGE!
Much Data
Why go Deep ?
65
No More Handcrafted Features !
66
[Kudos to Richard Socher, for this eloquent summary :) ]
• Manually designed features are often over-specified, incomplete
and take a long time to design and validate
• Learned Features are easy to adapt, fast to learn
• Deep learning provides a very flexible, (almost?) universal,
learnable framework for representing world, visual and
linguistic information.
• Deep learning can learn unsupervised (from raw text/audio/
images/whatever content) and supervised (with specific labels
like positive/negative)
Why Deep Learning ?
Deep Learning: Future Developments
Currently an explosion of developments
• Hessian-Free networks (2010)
• Long Short Term Memory (2011)
• Large Convolutional nets, max-pooling (2011)
• Nesterov’s Gradient Descent (2013)
Currently state of the art but...
• No way of doing logical inference (extrapolation)
• No easy integration of abstract knowledge
• Hypothetic space bias might not conform with reality
68
Deep Learning: Future Challenges
a
69
Szegedy, C., Wojciech, Z., Sutskever, I., Bruna, J., Erhan, D., Goodfellow, I., Fergus, R. (2013) Intriguing
properties of neural networks
L: correctly identified, Center: added noise x10, R: “Ostrich”
as PhD candidate KTH/CSC:
“Always interested in discussing
Machine Learning, Deep
Architectures, Graphs, and
Language Technology”
In touch!
roelof@kth.se
www.csc.kth.se/~roelof/
Data Science ConsultancyAcademic/Research
roelof@gve-systems.com
www.gve-systems.com
72
Gve Systems
Graph Technologies
• Theano - CPU/GPU symbolic expression compiler in
python (from LISA lab at University of Montreal).
http://deeplearning.net/software/theano/
• Pylearn2 - library designed to make machine learning
research easy. http://deeplearning.net/software/
pylearn2/
• Torch - Matlab-like environment for state-of-the-art
machine learning algorithms in lua (from Ronan
Collobert, Clement Farabet and Koray Kavukcuoglu)
http://torch.ch/
• more info: http://deeplearning.net/software links/
Wanna Play ?
Wanna Play ? General Deep Learning
73
• RNNLM (Mikolov)

http://rnnlm.org
• NB-SVM

https://github.com/mesnilgr/nbsvm
• Word2Vec (skipgrams/cbow)

https://code.google.com/p/word2vec/ (original)

http://radimrehurek.com/gensim/models/word2vec.html (python)
• GloVe

http://nlp.stanford.edu/projects/glove/ (original)

https://github.com/maciejkula/glove-python (python)
• Socher et al / Stanford RNN Sentiment code:

http://nlp.stanford.edu/sentiment/code.html
• Deep Learning without Magic Tutorial:

http://nlp.stanford.edu/courses/NAACL2013/
Wanna Play ? NLP
74
• cuda-convnet2 (Alex Krizhevsky, Toronto) (c++/
CUDA, optimized for GTX 580) 

https://code.google.com/p/cuda-convnet2/
• Caffe (Berkeley) (Cuda/OpenCL, Theano, Python)

http://caffe.berkeleyvision.org/
• OverFeat (NYU) 

http://cilvr.nyu.edu/doku.php?id=code:start
Wanna Play ? Computer Vision
75

Mais conteúdo relacionado

Mais procurados

Transfer Learning and Domain Adaptation (D2L3 2017 UPC Deep Learning for Comp...
Transfer Learning and Domain Adaptation (D2L3 2017 UPC Deep Learning for Comp...Transfer Learning and Domain Adaptation (D2L3 2017 UPC Deep Learning for Comp...
Transfer Learning and Domain Adaptation (D2L3 2017 UPC Deep Learning for Comp...Universitat Politècnica de Catalunya
 
The Transformer in Vision | Xavier Giro | Master in Computer Vision Barcelona...
The Transformer in Vision | Xavier Giro | Master in Computer Vision Barcelona...The Transformer in Vision | Xavier Giro | Master in Computer Vision Barcelona...
The Transformer in Vision | Xavier Giro | Master in Computer Vision Barcelona...Universitat Politècnica de Catalunya
 
A Beginner's Guide to Monocular Depth Estimation
A Beginner's Guide to Monocular Depth EstimationA Beginner's Guide to Monocular Depth Estimation
A Beginner's Guide to Monocular Depth EstimationRyo Takahashi
 
Introduction to CNN
Introduction to CNNIntroduction to CNN
Introduction to CNNShuai Zhang
 
Deep neural networks
Deep neural networksDeep neural networks
Deep neural networksSi Haem
 
Intro to deep learning
Intro to deep learning Intro to deep learning
Intro to deep learning David Voyles
 
Deep Learning - Convolutional Neural Networks
Deep Learning - Convolutional Neural NetworksDeep Learning - Convolutional Neural Networks
Deep Learning - Convolutional Neural NetworksChristian Perone
 
Convolutional Neural Networks (CNN)
Convolutional Neural Networks (CNN)Convolutional Neural Networks (CNN)
Convolutional Neural Networks (CNN)Gaurav Mittal
 
Convolutional neural network from VGG to DenseNet
Convolutional neural network from VGG to DenseNetConvolutional neural network from VGG to DenseNet
Convolutional neural network from VGG to DenseNetSungminYou
 
Convolution Neural Network (CNN)
Convolution Neural Network (CNN)Convolution Neural Network (CNN)
Convolution Neural Network (CNN)Suraj Aavula
 
Convolutional Neural Network - CNN | How CNN Works | Deep Learning Course | S...
Convolutional Neural Network - CNN | How CNN Works | Deep Learning Course | S...Convolutional Neural Network - CNN | How CNN Works | Deep Learning Course | S...
Convolutional Neural Network - CNN | How CNN Works | Deep Learning Course | S...Simplilearn
 
[기초개념] Graph Convolutional Network (GCN)
[기초개념] Graph Convolutional Network (GCN)[기초개념] Graph Convolutional Network (GCN)
[기초개념] Graph Convolutional Network (GCN)Donghyeon Kim
 
Deep learning - A Visual Introduction
Deep learning - A Visual IntroductionDeep learning - A Visual Introduction
Deep learning - A Visual IntroductionLukas Masuch
 
Introduction to Recurrent Neural Network
Introduction to Recurrent Neural NetworkIntroduction to Recurrent Neural Network
Introduction to Recurrent Neural NetworkKnoldus Inc.
 
Transformer in Computer Vision
Transformer in Computer VisionTransformer in Computer Vision
Transformer in Computer VisionDongmin Choi
 
ViT (Vision Transformer) Review [CDM]
ViT (Vision Transformer) Review [CDM]ViT (Vision Transformer) Review [CDM]
ViT (Vision Transformer) Review [CDM]Dongmin Choi
 

Mais procurados (20)

Transfer Learning and Domain Adaptation (D2L3 2017 UPC Deep Learning for Comp...
Transfer Learning and Domain Adaptation (D2L3 2017 UPC Deep Learning for Comp...Transfer Learning and Domain Adaptation (D2L3 2017 UPC Deep Learning for Comp...
Transfer Learning and Domain Adaptation (D2L3 2017 UPC Deep Learning for Comp...
 
The Transformer in Vision | Xavier Giro | Master in Computer Vision Barcelona...
The Transformer in Vision | Xavier Giro | Master in Computer Vision Barcelona...The Transformer in Vision | Xavier Giro | Master in Computer Vision Barcelona...
The Transformer in Vision | Xavier Giro | Master in Computer Vision Barcelona...
 
A Beginner's Guide to Monocular Depth Estimation
A Beginner's Guide to Monocular Depth EstimationA Beginner's Guide to Monocular Depth Estimation
A Beginner's Guide to Monocular Depth Estimation
 
Introduction to CNN
Introduction to CNNIntroduction to CNN
Introduction to CNN
 
Deep neural networks
Deep neural networksDeep neural networks
Deep neural networks
 
lecun-01.ppt
lecun-01.pptlecun-01.ppt
lecun-01.ppt
 
Intro to deep learning
Intro to deep learning Intro to deep learning
Intro to deep learning
 
Resnet
ResnetResnet
Resnet
 
Deep Learning - Convolutional Neural Networks
Deep Learning - Convolutional Neural NetworksDeep Learning - Convolutional Neural Networks
Deep Learning - Convolutional Neural Networks
 
Convolutional Neural Networks (CNN)
Convolutional Neural Networks (CNN)Convolutional Neural Networks (CNN)
Convolutional Neural Networks (CNN)
 
Convolutional neural network from VGG to DenseNet
Convolutional neural network from VGG to DenseNetConvolutional neural network from VGG to DenseNet
Convolutional neural network from VGG to DenseNet
 
Convolution Neural Network (CNN)
Convolution Neural Network (CNN)Convolution Neural Network (CNN)
Convolution Neural Network (CNN)
 
cnn ppt.pptx
cnn ppt.pptxcnn ppt.pptx
cnn ppt.pptx
 
Convolutional Neural Network - CNN | How CNN Works | Deep Learning Course | S...
Convolutional Neural Network - CNN | How CNN Works | Deep Learning Course | S...Convolutional Neural Network - CNN | How CNN Works | Deep Learning Course | S...
Convolutional Neural Network - CNN | How CNN Works | Deep Learning Course | S...
 
[기초개념] Graph Convolutional Network (GCN)
[기초개념] Graph Convolutional Network (GCN)[기초개념] Graph Convolutional Network (GCN)
[기초개념] Graph Convolutional Network (GCN)
 
Deep learning - A Visual Introduction
Deep learning - A Visual IntroductionDeep learning - A Visual Introduction
Deep learning - A Visual Introduction
 
Deep learning
Deep learningDeep learning
Deep learning
 
Introduction to Recurrent Neural Network
Introduction to Recurrent Neural NetworkIntroduction to Recurrent Neural Network
Introduction to Recurrent Neural Network
 
Transformer in Computer Vision
Transformer in Computer VisionTransformer in Computer Vision
Transformer in Computer Vision
 
ViT (Vision Transformer) Review [CDM]
ViT (Vision Transformer) Review [CDM]ViT (Vision Transformer) Review [CDM]
ViT (Vision Transformer) Review [CDM]
 

Semelhante a Deep Learning: a birds eye view

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
 
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
 
MLIP - Chapter 3 - Introduction to deep learning
MLIP - Chapter 3 - Introduction to deep learningMLIP - Chapter 3 - Introduction to deep learning
MLIP - Chapter 3 - Introduction to deep learningCharles Deledalle
 
Deep Learning @ ZHAW Datalab (with Mark Cieliebak & Yves Pauchard)
Deep Learning @ ZHAW Datalab (with Mark Cieliebak & Yves Pauchard)Deep Learning @ ZHAW Datalab (with Mark Cieliebak & Yves Pauchard)
Deep Learning @ ZHAW Datalab (with Mark Cieliebak & Yves Pauchard)Thilo Stadelmann
 
Introduction to deep learning
Introduction to deep learningIntroduction to deep learning
Introduction to deep learningAmr Rashed
 
Deep learning: the future of recommendations
Deep learning: the future of recommendationsDeep learning: the future of recommendations
Deep learning: the future of recommendationsBalázs Hidasi
 
Deep Learning for NLP: An Introduction to Neural Word Embeddings
Deep Learning for NLP: An Introduction to Neural Word EmbeddingsDeep Learning for NLP: An Introduction to Neural Word Embeddings
Deep Learning for NLP: An Introduction to Neural Word EmbeddingsRoelof Pieters
 
"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
 
Multi modal retrieval and generation with deep distributed models
Multi modal retrieval and generation with deep distributed modelsMulti modal retrieval and generation with deep distributed models
Multi modal retrieval and generation with deep distributed modelsRoelof Pieters
 
Deep Learning And Business Models (VNITC 2015-09-13)
Deep Learning And Business Models (VNITC 2015-09-13)Deep Learning And Business Models (VNITC 2015-09-13)
Deep Learning And Business Models (VNITC 2015-09-13)Ha Phuong
 
Deep Learning for Information Retrieval
Deep Learning for Information RetrievalDeep Learning for Information Retrieval
Deep Learning for Information RetrievalRoelof Pieters
 
Yann le cun
Yann le cunYann le cun
Yann le cunYandex
 
DEF CON 24 - Clarence Chio - machine duping 101
DEF CON 24 - Clarence Chio - machine duping 101DEF CON 24 - Clarence Chio - machine duping 101
DEF CON 24 - Clarence Chio - machine duping 101Felipe Prado
 
Deep Learning Made Easy with Deep Features
Deep Learning Made Easy with Deep FeaturesDeep Learning Made Easy with Deep Features
Deep Learning Made Easy with Deep FeaturesTuri, Inc.
 
Transferring Software Testing Tools to Practice
Transferring Software Testing Tools to PracticeTransferring Software Testing Tools to Practice
Transferring Software Testing Tools to PracticeTao Xie
 
Quoc le, slides MLconf 11/15/13
Quoc le, slides  MLconf 11/15/13Quoc le, slides  MLconf 11/15/13
Quoc le, slides MLconf 11/15/13MLconf
 
Transfer Learning: Breve introducción a modelos pre-entrenados.
Transfer Learning: Breve introducción a modelos pre-entrenados.Transfer Learning: Breve introducción a modelos pre-entrenados.
Transfer Learning: Breve introducción a modelos pre-entrenados.Fernando Constantino
 
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
 
MDEC Data Matters Series: machine learning and Deep Learning, A Primer
MDEC Data Matters Series: machine learning and Deep Learning, A PrimerMDEC Data Matters Series: machine learning and Deep Learning, A Primer
MDEC Data Matters Series: machine learning and Deep Learning, A PrimerPoo Kuan Hoong
 

Semelhante a Deep Learning: a birds eye view (20)

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
 
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!
 
MLIP - Chapter 3 - Introduction to deep learning
MLIP - Chapter 3 - Introduction to deep learningMLIP - Chapter 3 - Introduction to deep learning
MLIP - Chapter 3 - Introduction to deep learning
 
Deep Learning @ ZHAW Datalab (with Mark Cieliebak & Yves Pauchard)
Deep Learning @ ZHAW Datalab (with Mark Cieliebak & Yves Pauchard)Deep Learning @ ZHAW Datalab (with Mark Cieliebak & Yves Pauchard)
Deep Learning @ ZHAW Datalab (with Mark Cieliebak & Yves Pauchard)
 
Introduction to deep learning
Introduction to deep learningIntroduction to deep learning
Introduction to deep learning
 
Deep learning: the future of recommendations
Deep learning: the future of recommendationsDeep learning: the future of recommendations
Deep learning: the future of recommendations
 
Deep Learning for NLP: An Introduction to Neural Word Embeddings
Deep Learning for NLP: An Introduction to Neural Word EmbeddingsDeep Learning for NLP: An Introduction to Neural Word Embeddings
Deep Learning for NLP: An Introduction to Neural Word Embeddings
 
"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...
 
Multi modal retrieval and generation with deep distributed models
Multi modal retrieval and generation with deep distributed modelsMulti modal retrieval and generation with deep distributed models
Multi modal retrieval and generation with deep distributed models
 
Deep Learning And Business Models (VNITC 2015-09-13)
Deep Learning And Business Models (VNITC 2015-09-13)Deep Learning And Business Models (VNITC 2015-09-13)
Deep Learning And Business Models (VNITC 2015-09-13)
 
Deep Learning for Information Retrieval
Deep Learning for Information RetrievalDeep Learning for Information Retrieval
Deep Learning for Information Retrieval
 
Yann le cun
Yann le cunYann le cun
Yann le cun
 
DEF CON 24 - Clarence Chio - machine duping 101
DEF CON 24 - Clarence Chio - machine duping 101DEF CON 24 - Clarence Chio - machine duping 101
DEF CON 24 - Clarence Chio - machine duping 101
 
Deep Learning Made Easy with Deep Features
Deep Learning Made Easy with Deep FeaturesDeep Learning Made Easy with Deep Features
Deep Learning Made Easy with Deep Features
 
MILA DL & RL summer school highlights
MILA DL & RL summer school highlights MILA DL & RL summer school highlights
MILA DL & RL summer school highlights
 
Transferring Software Testing Tools to Practice
Transferring Software Testing Tools to PracticeTransferring Software Testing Tools to Practice
Transferring Software Testing Tools to Practice
 
Quoc le, slides MLconf 11/15/13
Quoc le, slides  MLconf 11/15/13Quoc le, slides  MLconf 11/15/13
Quoc le, slides MLconf 11/15/13
 
Transfer Learning: Breve introducción a modelos pre-entrenados.
Transfer Learning: Breve introducción a modelos pre-entrenados.Transfer Learning: Breve introducción a modelos pre-entrenados.
Transfer Learning: Breve introducción a modelos pre-entrenados.
 
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?
 
MDEC Data Matters Series: machine learning and Deep Learning, A Primer
MDEC Data Matters Series: machine learning and Deep Learning, A PrimerMDEC Data Matters Series: machine learning and Deep Learning, A Primer
MDEC Data Matters Series: machine learning and Deep Learning, A Primer
 

Mais de Roelof Pieters

Speculations in anthropology and tech for an uncertain future
Speculations in anthropology and tech for an uncertain futureSpeculations in anthropology and tech for an uncertain future
Speculations in anthropology and tech for an uncertain futureRoelof Pieters
 
AI assisted creativity
AI assisted creativity AI assisted creativity
AI assisted creativity Roelof Pieters
 
Creativity and AI: 
Deep Neural Nets "Going Wild"
Creativity and AI: 
Deep Neural Nets "Going Wild"Creativity and AI: 
Deep Neural Nets "Going Wild"
Creativity and AI: 
Deep Neural Nets "Going Wild"Roelof Pieters
 
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
 
Building a Deep Learning (Dream) Machine
Building a Deep Learning (Dream) MachineBuilding a Deep Learning (Dream) Machine
Building a Deep Learning (Dream) MachineRoelof Pieters
 
Multi-modal embeddings: from discriminative to generative models and creative ai
Multi-modal embeddings: from discriminative to generative models and creative aiMulti-modal embeddings: from discriminative to generative models and creative ai
Multi-modal embeddings: from discriminative to generative models and creative aiRoelof Pieters
 
Deep learning for natural language embeddings
Deep learning for natural language embeddingsDeep learning for natural language embeddings
Deep learning for natural language embeddingsRoelof Pieters
 
Deep Learning for Natural Language Processing: Word Embeddings
Deep Learning for Natural Language Processing: Word EmbeddingsDeep Learning for Natural Language Processing: Word Embeddings
Deep Learning for Natural Language Processing: Word EmbeddingsRoelof Pieters
 
Creative AI & multimodality: looking ahead
Creative AI & multimodality: looking aheadCreative AI & multimodality: looking ahead
Creative AI & multimodality: looking aheadRoelof Pieters
 
Python for Image Understanding: Deep Learning with Convolutional Neural Nets
Python for Image Understanding: Deep Learning with Convolutional Neural NetsPython for Image Understanding: Deep Learning with Convolutional Neural Nets
Python for Image Understanding: Deep Learning with Convolutional Neural NetsRoelof Pieters
 
Explore Data: Data Science + Visualization
Explore Data: Data Science + VisualizationExplore Data: Data Science + Visualization
Explore Data: Data Science + VisualizationRoelof Pieters
 
Deep Learning as a Cat/Dog Detector
Deep Learning as a Cat/Dog DetectorDeep Learning as a Cat/Dog Detector
Deep Learning as a Cat/Dog DetectorRoelof Pieters
 
Graph, Data-science, and Deep Learning
Graph, Data-science, and Deep LearningGraph, Data-science, and Deep Learning
Graph, Data-science, and Deep LearningRoelof Pieters
 
Learning to understand phrases by embedding the dictionary
Learning to understand phrases by embedding the dictionaryLearning to understand phrases by embedding the dictionary
Learning to understand phrases by embedding the dictionaryRoelof Pieters
 
Zero shot learning through cross-modal transfer
Zero shot learning through cross-modal transferZero shot learning through cross-modal transfer
Zero shot learning through cross-modal transferRoelof Pieters
 
Visual-Semantic Embeddings: some thoughts on Language
Visual-Semantic Embeddings: some thoughts on LanguageVisual-Semantic Embeddings: some thoughts on Language
Visual-Semantic Embeddings: some thoughts on LanguageRoelof Pieters
 
Recommender Systems, Matrices and Graphs
Recommender Systems, Matrices and GraphsRecommender Systems, Matrices and Graphs
Recommender Systems, Matrices and GraphsRoelof Pieters
 
Hackathon 2014 NLP Hack
Hackathon 2014 NLP HackHackathon 2014 NLP Hack
Hackathon 2014 NLP HackRoelof Pieters
 

Mais de Roelof Pieters (18)

Speculations in anthropology and tech for an uncertain future
Speculations in anthropology and tech for an uncertain futureSpeculations in anthropology and tech for an uncertain future
Speculations in anthropology and tech for an uncertain future
 
AI assisted creativity
AI assisted creativity AI assisted creativity
AI assisted creativity
 
Creativity and AI: 
Deep Neural Nets "Going Wild"
Creativity and AI: 
Deep Neural Nets "Going Wild"Creativity and AI: 
Deep Neural Nets "Going Wild"
Creativity and AI: 
Deep Neural Nets "Going Wild"
 
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
 
Building a Deep Learning (Dream) Machine
Building a Deep Learning (Dream) MachineBuilding a Deep Learning (Dream) Machine
Building a Deep Learning (Dream) Machine
 
Multi-modal embeddings: from discriminative to generative models and creative ai
Multi-modal embeddings: from discriminative to generative models and creative aiMulti-modal embeddings: from discriminative to generative models and creative ai
Multi-modal embeddings: from discriminative to generative models and creative ai
 
Deep learning for natural language embeddings
Deep learning for natural language embeddingsDeep learning for natural language embeddings
Deep learning for natural language embeddings
 
Deep Learning for Natural Language Processing: Word Embeddings
Deep Learning for Natural Language Processing: Word EmbeddingsDeep Learning for Natural Language Processing: Word Embeddings
Deep Learning for Natural Language Processing: Word Embeddings
 
Creative AI & multimodality: looking ahead
Creative AI & multimodality: looking aheadCreative AI & multimodality: looking ahead
Creative AI & multimodality: looking ahead
 
Python for Image Understanding: Deep Learning with Convolutional Neural Nets
Python for Image Understanding: Deep Learning with Convolutional Neural NetsPython for Image Understanding: Deep Learning with Convolutional Neural Nets
Python for Image Understanding: Deep Learning with Convolutional Neural Nets
 
Explore Data: Data Science + Visualization
Explore Data: Data Science + VisualizationExplore Data: Data Science + Visualization
Explore Data: Data Science + Visualization
 
Deep Learning as a Cat/Dog Detector
Deep Learning as a Cat/Dog DetectorDeep Learning as a Cat/Dog Detector
Deep Learning as a Cat/Dog Detector
 
Graph, Data-science, and Deep Learning
Graph, Data-science, and Deep LearningGraph, Data-science, and Deep Learning
Graph, Data-science, and Deep Learning
 
Learning to understand phrases by embedding the dictionary
Learning to understand phrases by embedding the dictionaryLearning to understand phrases by embedding the dictionary
Learning to understand phrases by embedding the dictionary
 
Zero shot learning through cross-modal transfer
Zero shot learning through cross-modal transferZero shot learning through cross-modal transfer
Zero shot learning through cross-modal transfer
 
Visual-Semantic Embeddings: some thoughts on Language
Visual-Semantic Embeddings: some thoughts on LanguageVisual-Semantic Embeddings: some thoughts on Language
Visual-Semantic Embeddings: some thoughts on Language
 
Recommender Systems, Matrices and Graphs
Recommender Systems, Matrices and GraphsRecommender Systems, Matrices and Graphs
Recommender Systems, Matrices and Graphs
 
Hackathon 2014 NLP Hack
Hackathon 2014 NLP HackHackathon 2014 NLP Hack
Hackathon 2014 NLP Hack
 

Último

Cloud Frontiers: A Deep Dive into Serverless Spatial Data and FME
Cloud Frontiers:  A Deep Dive into Serverless Spatial Data and FMECloud Frontiers:  A Deep Dive into Serverless Spatial Data and FME
Cloud Frontiers: A Deep Dive into Serverless Spatial Data and FMESafe Software
 
WSO2's API Vision: Unifying Control, Empowering Developers
WSO2's API Vision: Unifying Control, Empowering DevelopersWSO2's API Vision: Unifying Control, Empowering Developers
WSO2's API Vision: Unifying Control, Empowering DevelopersWSO2
 
TrustArc Webinar - Unlock the Power of AI-Driven Data Discovery
TrustArc Webinar - Unlock the Power of AI-Driven Data DiscoveryTrustArc Webinar - Unlock the Power of AI-Driven Data Discovery
TrustArc Webinar - Unlock the Power of AI-Driven Data DiscoveryTrustArc
 
Vector Search -An Introduction in Oracle Database 23ai.pptx
Vector Search -An Introduction in Oracle Database 23ai.pptxVector Search -An Introduction in Oracle Database 23ai.pptx
Vector Search -An Introduction in Oracle Database 23ai.pptxRemote DBA Services
 
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
 
How to Troubleshoot Apps for the Modern Connected Worker
How to Troubleshoot Apps for the Modern Connected WorkerHow to Troubleshoot Apps for the Modern Connected Worker
How to Troubleshoot Apps for the Modern Connected WorkerThousandEyes
 
Why Teams call analytics are critical to your entire business
Why Teams call analytics are critical to your entire businessWhy Teams call analytics are critical to your entire business
Why Teams call analytics are critical to your entire businesspanagenda
 
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
 
MS Copilot expands with MS Graph connectors
MS Copilot expands with MS Graph connectorsMS Copilot expands with MS Graph connectors
MS Copilot expands with MS Graph connectorsNanddeep Nachan
 
Biography Of Angeliki Cooney | Senior Vice President Life Sciences | Albany, ...
Biography Of Angeliki Cooney | Senior Vice President Life Sciences | Albany, ...Biography Of Angeliki Cooney | Senior Vice President Life Sciences | Albany, ...
Biography Of Angeliki Cooney | Senior Vice President Life Sciences | Albany, ...Angeliki Cooney
 
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
 
Web Form Automation for Bonterra Impact Management (fka Social Solutions Apri...
Web Form Automation for Bonterra Impact Management (fka Social Solutions Apri...Web Form Automation for Bonterra Impact Management (fka Social Solutions Apri...
Web Form Automation for Bonterra Impact Management (fka Social Solutions Apri...Jeffrey Haguewood
 
Corporate and higher education May webinar.pptx
Corporate and higher education May webinar.pptxCorporate and higher education May webinar.pptx
Corporate and higher education May webinar.pptxRustici Software
 
Platformless Horizons for Digital Adaptability
Platformless Horizons for Digital AdaptabilityPlatformless Horizons for Digital Adaptability
Platformless Horizons for Digital AdaptabilityWSO2
 
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
 
MINDCTI Revenue Release Quarter One 2024
MINDCTI Revenue Release Quarter One 2024MINDCTI Revenue Release Quarter One 2024
MINDCTI Revenue Release Quarter One 2024MIND CTI
 
Architecting Cloud Native Applications
Architecting Cloud Native ApplicationsArchitecting Cloud Native Applications
Architecting Cloud Native ApplicationsWSO2
 
Apidays New York 2024 - APIs in 2030: The Risk of Technological Sleepwalk by ...
Apidays New York 2024 - APIs in 2030: The Risk of Technological Sleepwalk by ...Apidays New York 2024 - APIs in 2030: The Risk of Technological Sleepwalk by ...
Apidays New York 2024 - APIs in 2030: The Risk of Technological Sleepwalk by ...apidays
 
Apidays New York 2024 - The Good, the Bad and the Governed by David O'Neill, ...
Apidays New York 2024 - The Good, the Bad and the Governed by David O'Neill, ...Apidays New York 2024 - The Good, the Bad and the Governed by David O'Neill, ...
Apidays New York 2024 - The Good, the Bad and the Governed by David O'Neill, ...apidays
 
EMPOWERMENT TECHNOLOGY GRADE 11 QUARTER 2 REVIEWER
EMPOWERMENT TECHNOLOGY GRADE 11 QUARTER 2 REVIEWEREMPOWERMENT TECHNOLOGY GRADE 11 QUARTER 2 REVIEWER
EMPOWERMENT TECHNOLOGY GRADE 11 QUARTER 2 REVIEWERMadyBayot
 

Último (20)

Cloud Frontiers: A Deep Dive into Serverless Spatial Data and FME
Cloud Frontiers:  A Deep Dive into Serverless Spatial Data and FMECloud Frontiers:  A Deep Dive into Serverless Spatial Data and FME
Cloud Frontiers: A Deep Dive into Serverless Spatial Data and FME
 
WSO2's API Vision: Unifying Control, Empowering Developers
WSO2's API Vision: Unifying Control, Empowering DevelopersWSO2's API Vision: Unifying Control, Empowering Developers
WSO2's API Vision: Unifying Control, Empowering Developers
 
TrustArc Webinar - Unlock the Power of AI-Driven Data Discovery
TrustArc Webinar - Unlock the Power of AI-Driven Data DiscoveryTrustArc Webinar - Unlock the Power of AI-Driven Data Discovery
TrustArc Webinar - Unlock the Power of AI-Driven Data Discovery
 
Vector Search -An Introduction in Oracle Database 23ai.pptx
Vector Search -An Introduction in Oracle Database 23ai.pptxVector Search -An Introduction in Oracle Database 23ai.pptx
Vector Search -An Introduction in Oracle Database 23ai.pptx
 
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
 
How to Troubleshoot Apps for the Modern Connected Worker
How to Troubleshoot Apps for the Modern Connected WorkerHow to Troubleshoot Apps for the Modern Connected Worker
How to Troubleshoot Apps for the Modern Connected Worker
 
Why Teams call analytics are critical to your entire business
Why Teams call analytics are critical to your entire businessWhy Teams call analytics are critical to your entire business
Why Teams call analytics are critical to your entire business
 
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
 
MS Copilot expands with MS Graph connectors
MS Copilot expands with MS Graph connectorsMS Copilot expands with MS Graph connectors
MS Copilot expands with MS Graph connectors
 
Biography Of Angeliki Cooney | Senior Vice President Life Sciences | Albany, ...
Biography Of Angeliki Cooney | Senior Vice President Life Sciences | Albany, ...Biography Of Angeliki Cooney | Senior Vice President Life Sciences | Albany, ...
Biography Of Angeliki Cooney | Senior Vice President Life Sciences | Albany, ...
 
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
 
Web Form Automation for Bonterra Impact Management (fka Social Solutions Apri...
Web Form Automation for Bonterra Impact Management (fka Social Solutions Apri...Web Form Automation for Bonterra Impact Management (fka Social Solutions Apri...
Web Form Automation for Bonterra Impact Management (fka Social Solutions Apri...
 
Corporate and higher education May webinar.pptx
Corporate and higher education May webinar.pptxCorporate and higher education May webinar.pptx
Corporate and higher education May webinar.pptx
 
Platformless Horizons for Digital Adaptability
Platformless Horizons for Digital AdaptabilityPlatformless Horizons for Digital Adaptability
Platformless Horizons for Digital Adaptability
 
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...
 
MINDCTI Revenue Release Quarter One 2024
MINDCTI Revenue Release Quarter One 2024MINDCTI Revenue Release Quarter One 2024
MINDCTI Revenue Release Quarter One 2024
 
Architecting Cloud Native Applications
Architecting Cloud Native ApplicationsArchitecting Cloud Native Applications
Architecting Cloud Native Applications
 
Apidays New York 2024 - APIs in 2030: The Risk of Technological Sleepwalk by ...
Apidays New York 2024 - APIs in 2030: The Risk of Technological Sleepwalk by ...Apidays New York 2024 - APIs in 2030: The Risk of Technological Sleepwalk by ...
Apidays New York 2024 - APIs in 2030: The Risk of Technological Sleepwalk by ...
 
Apidays New York 2024 - The Good, the Bad and the Governed by David O'Neill, ...
Apidays New York 2024 - The Good, the Bad and the Governed by David O'Neill, ...Apidays New York 2024 - The Good, the Bad and the Governed by David O'Neill, ...
Apidays New York 2024 - The Good, the Bad and the Governed by David O'Neill, ...
 
EMPOWERMENT TECHNOLOGY GRADE 11 QUARTER 2 REVIEWER
EMPOWERMENT TECHNOLOGY GRADE 11 QUARTER 2 REVIEWEREMPOWERMENT TECHNOLOGY GRADE 11 QUARTER 2 REVIEWER
EMPOWERMENT TECHNOLOGY GRADE 11 QUARTER 2 REVIEWER
 

Deep Learning: a birds eye view

  • 1. @graphific Roelof Pieters Deep Learning:
 a (non-techy) birds-eye view 20  April  2015   Stockholm Deep Learning Slides at:
 http://www.slideshare.net/roelofp/deep-learning-a-birdseye-view
  • 2. • Deals with “construction and study of systems that can learn from data” Refresher: Machine Learning ??? A computer program is said to learn from experience (E) with respect to some class of tasks (T) and performance measure (P), if its performance at tasks in T, as measured by P, improves with experience E — T. Mitchell 1997 2
  • 3. Improving some task T based on experience E with respect to performance measure P. Deep Learning = Machine Learning Learning denotes changes in the system that are adaptive in the sense that they enable the system to do the same task (or tasks drawn from a population of similar tasks) more effectively the next time. — H. Simon 1983 
 "Why Should Machines Learn?” in Mitchell 1997 — T. Mitchell 1997 3
  • 4. Representation learning Attempts to automatically learn good features or representations Deep learning Attempt to learn multiple levels of representation of increasing complexity/abstraction Deep Learning: What? 4
  • 6. Machine Learning ?? Traditional Programming: Data Program Output 6 Computer
  • 7. Machine Learning ?? Traditional Programming: Data Program Output Data Program Output Machine Learning: 7 (labels) (“weights”/model) Computer Computer
  • 8. Machine Learning ?? 8 • Most machine learning methods work well because of human-designed/hand- engineered features (representations) • machine learning -> optimising weights to best make a final prediction
  • 9. Typical ML Regression Deep Learning: Why?
  • 10. Neural NetTypical ML Regression Deep Learning: Why?
  • 12. Machine ->Deep Learning ?? DEEP NET 
 (DEEP LEARNING)
  • 13.
  • 16. Deep Learning is everywhere…
  • 17.
  • 18. Deep Learning in the News
  • 20. (source: arXiv bookworm, Culturomics) Scientific Articles:
  • 21.
  • 22.
  • 23.
  • 24.
  • 25. Why Now? • Inspired by the architectural depth of the brain, researchers wanted for decades to train deep multi-layer neural networks. • No successful attempts were reported before 2006 …Exception: convolutional neural networks, LeCun 1998 • SVM: Vapnik and his co-workers developed the Support Vector Machine (1993) (shallow architecture). • Breakthrough in 2006! 25
  • 26. Renewed Interest: 1990s • Learning multiple layers • “Back propagation” • Can “theoretically” learn any function! But… • Very slow and inefficient • SVMs, random forests, etc. SOTA 26
  • 27. 2006 Breakthrough • More data • Faster hardware: GPU’s, multi-core CPU’s • Working ideas on how to train deep architectures 27
  • 28. 2006 Breakthrough • More data • Faster hardware: GPU’s, multi-core CPU’s • Working ideas on how to train deep architectures 28
  • 31. 2006 Breakthrough • More data • Faster hardware: GPU’s, multi-core CPU’s • Working ideas on how to train deep architectures 31
  • 33. Rise of Raw Computation Power
  • 34. 2006 Breakthrough • More data • Faster hardware: GPU’s, multi-core CPU’s • Working ideas on how to train deep architectures 34
  • 35. 2006 Breakthrough Stacked Restricted Boltzman Machines* (RBM) Hinton, G. E, Osindero, S., and Teh, Y. W. (2006).
 A fast learning algorithm for deep belief nets.
 Neural Computation, 18:1527-1554. Stacked Autoencoders (AE) Bengio, Y., Lamblin, P., Popovici, P., Larochelle, H. (2007).
 Greedy Layer-Wise Training of Deep Networks,
 Advances in Neural Information Processing Systems 19 * called Deep Belief Networks (DBN)
35
  • 36. Deep Learning for the Win!
  • 37. • 1.2M images with 1000 object categories • AlexNet of uni Toronto: 15% error rate vs 26% for 2th placed (traditional CV) Impact on Computer Vision ImageNet Challenge 2012
  • 38. Impact on Computer Vision (from Clarifai)
  • 40. 40 Classification results on ImageNet 2012 Team Year Place Error (top-5) Uses external data SuperVision 2012 - 16.4% no SuperVision 2012 1st 15.3% ImageNet 22k Clarifai 2013 - 11.7% no Clarifai 2013 1st 11.2% ImageNet 22k MSRA 2014 3rd 7.35% no VGG 2014 2nd 7.32% no GoogLeNet 2014 1st 6.67% no Final Detection Results Team Year Place mAP e x t e r n a l data ensemble c o n t e x t u a l model approach UvA-Euvision 2013 1st 22.6% none ? yes F i s h e r vectors Deep Insight 2014 3rd 40.5% I L S V R C 1 2 Classification + Localization 3 models yes ConvNet C U H K DeepID-Net 2014 2nd 40.7% I L S V R C 1 2 Classification + Localization ? no ConvNet GoogLeNet 2014 1st 43.9% I L S V R C 1 2 Classification 6 models no ConvNet Detection results source: Szegedy et al. Going deeper with convolutions (GoogLeNet ), ILSVRC2014, 19 Sep 2014
  • 41. 41source: Szegedy et al. Going deeper with convolutions (GoogLeNet ), ILSVRC2014, 19 Sep 2014 GoogLeNet Convolution Pooling Softmax Other Winners of: 
 Large Scale Visual Recognition Challenge 2014 
 (ILSVRC2014) 19 September 2014 GoogLeNet Convolution Pooling Softmax Other
  • 42. 42source: Szegedy et al. Going deeper with convolutions (GoogLeNet ), ILSVRC2014, 19 Sep 2014 Inception Width of inception modules ranges from 256 filters (in early modules) to 1024 in top inception modules. Can remove fully connected layers on top completely Number of parameters is reduced to 5 million 256 480 480 512 512 512 832 832 1024 Computional cost is increased by less than 2X compared to Krizhevsky’s network. (<1.5Bn operations/evaluation)
  • 43. Impact on Computer Vision Latest State of the Art:
  • 44. Computer Vision: Current State of the Art
  • 45. Impact on Audio Processing 45 First public Breakthrough with Deep Learning in 2010 Dahl et al. (2010)

  • 46. Impact on Audio Processing 46 First public Breakthrough with Deep Learning in 2010 Dahl et al. (2010)
 -33%! -32%!
  • 47. Impact on Audio Processing 47 Speech Recognition
  • 48. Impact on Audio Processing 48 TIMIT Speech Recognition (from: Clarifai)
  • 49. Impact on Audio Processing
  • 50. C&W 2011 Impact on Natural Language Processing Pos: Toutanova et al.
 2003) Ner: Ando & Zhang 
 2005 C&W 2011
  • 51. Impact on Natural Language Processing Named Entity Recognition:
  • 54. Deep Architectures can be representationally efficient • Fewer computational units for same function Deep Representations might allow for a hierarchy or representation • Allows non-local generalisation • Comprehensibility Multiple levels of latent variables allow combinatorial sharing of statistical strength 54 Deep Learning: Why?
  • 55. — Andrew Ng “I’ve worked all my life in Machine Learning, and I’ve never seen one algorithm knock over benchmarks like Deep Learning” Deep Learning: Why? 55
  • 56. Biological Justification Deep Learning = Brain “inspired”
 Audio/Visual Cortex has multiple stages == Hierarchical
  • 57. Different Levels of Abstraction 57
  • 58. Hierarchical Learning • Natural progression from low level to high level structure as seen in natural complexity Different Levels of Abstraction Feature Representation 58
  • 59. Hierarchical Learning • Natural progression from low level to high level structure as seen in natural complexity• Easier to monitor what is being learnt and to guide the machine to better subspaces Different Levels of Abstraction Feature Representation 59
  • 60. Hierarchical Learning • Natural progression from low level to high level structure as seen in natural complexity• Easier to monitor what is being learnt and to guide the machine to better subspaces • A good lower level representation can be used for many distinct tasks Different Levels of Abstraction Feature Representation 60
  • 61. Hierarchical Learning • Natural progression from low level to high level structure as seen in natural complexity• Easier to monitor what is being learnt and to guide the machine to better subspaces • A good lower level representation can be used for many distinct tasks Different Levels of Abstraction Feature Representation 61
  • 62. Different Levels of Abstraction
  • 63. Classic Deep Architecture Input layer Hidden layers Output layer
  • 64. Modern Deep Architecture Input layer Hidden layers Output layer movie time: http://www.cs.toronto.edu/~hinton/adi/index.htm
  • 66. No More Handcrafted Features ! 66
  • 67. [Kudos to Richard Socher, for this eloquent summary :) ] • Manually designed features are often over-specified, incomplete and take a long time to design and validate • Learned Features are easy to adapt, fast to learn • Deep learning provides a very flexible, (almost?) universal, learnable framework for representing world, visual and linguistic information. • Deep learning can learn unsupervised (from raw text/audio/ images/whatever content) and supervised (with specific labels like positive/negative) Why Deep Learning ?
  • 68. Deep Learning: Future Developments Currently an explosion of developments • Hessian-Free networks (2010) • Long Short Term Memory (2011) • Large Convolutional nets, max-pooling (2011) • Nesterov’s Gradient Descent (2013) Currently state of the art but... • No way of doing logical inference (extrapolation) • No easy integration of abstract knowledge • Hypothetic space bias might not conform with reality 68
  • 69. Deep Learning: Future Challenges a 69 Szegedy, C., Wojciech, Z., Sutskever, I., Bruna, J., Erhan, D., Goodfellow, I., Fergus, R. (2013) Intriguing properties of neural networks L: correctly identified, Center: added noise x10, R: “Ostrich”
  • 70.
  • 71.
  • 72. as PhD candidate KTH/CSC: “Always interested in discussing Machine Learning, Deep Architectures, Graphs, and Language Technology” In touch! roelof@kth.se www.csc.kth.se/~roelof/ Data Science ConsultancyAcademic/Research roelof@gve-systems.com www.gve-systems.com 72 Gve Systems Graph Technologies
  • 73. • Theano - CPU/GPU symbolic expression compiler in python (from LISA lab at University of Montreal). http://deeplearning.net/software/theano/ • Pylearn2 - library designed to make machine learning research easy. http://deeplearning.net/software/ pylearn2/ • Torch - Matlab-like environment for state-of-the-art machine learning algorithms in lua (from Ronan Collobert, Clement Farabet and Koray Kavukcuoglu) http://torch.ch/ • more info: http://deeplearning.net/software links/ Wanna Play ? Wanna Play ? General Deep Learning 73
  • 74. • RNNLM (Mikolov)
 http://rnnlm.org • NB-SVM
 https://github.com/mesnilgr/nbsvm • Word2Vec (skipgrams/cbow)
 https://code.google.com/p/word2vec/ (original)
 http://radimrehurek.com/gensim/models/word2vec.html (python) • GloVe
 http://nlp.stanford.edu/projects/glove/ (original)
 https://github.com/maciejkula/glove-python (python) • Socher et al / Stanford RNN Sentiment code:
 http://nlp.stanford.edu/sentiment/code.html • Deep Learning without Magic Tutorial:
 http://nlp.stanford.edu/courses/NAACL2013/ Wanna Play ? NLP 74
  • 75. • cuda-convnet2 (Alex Krizhevsky, Toronto) (c++/ CUDA, optimized for GTX 580) 
 https://code.google.com/p/cuda-convnet2/ • Caffe (Berkeley) (Cuda/OpenCL, Theano, Python)
 http://caffe.berkeleyvision.org/ • OverFeat (NYU) 
 http://cilvr.nyu.edu/doku.php?id=code:start Wanna Play ? Computer Vision 75