SlideShare une entreprise Scribd logo
1  sur  41
Télécharger pour lire hors ligne
February 19th, 2015
Data Science Consulting
Héloïse Nonne, Data Scientist
Big Data & deep learning
CINaM, Aix-Marseille University
Big Data?
Big Data?
Explosion of data size
Falling cost of data
storage
Increase of
computing power
“Information is the oil of the 21st century, and analytics is the combustion engine.”
Peter Sondergaard, Senior Vice President, Gartner Research
The falling cost of data storage
1980 1990 2000 2014
300 000 $ 1 000 $ 100$ 0,1$
1956
IBM 350 RAMAC
Capacity: 3.75 MB
Storage cost for 1 Go
Data growing exponentially
• Over 90% of all the data in the
world was created in the past 2
years.
• Now, every year, 2 ZB are generated
1 ZB (zettabyte) = 1 trillion GB
• IDC (International Data Corporation)
predicts a generation of 40 ZB in
2020
• Around 100 hours of video are
uploaded to YouTube every minute
• Today’s datacenters occupy an area
of land equal in size to almost 6,000
football fields
Where data comes from?
Two approaches to large databases
Total failure rate = product of local failure rates
Design for failure at software level
Source; www.tomshardware.com
High-Tech hardware
• Roughly double the cost of commodity
• Roughly 5% failure rate
Commodity (≠ low end) hardware
• Roughly half the cost
• Roughly 10-15% failure rate
Distribution algorithm: MapReduce
Key principles of a DFS
• Duplication of data
• Distribution of data
• Colocalization of treatments
• Parallel treatments
• Horizontal and vertical elasticity
Hadoop Distributed File System (HDFS) / Computing
Distribution of data over multiple servers
Yes but, what for?
Big Data is about having
an understanding of what your relationship is with the people who are the most
important to you
and an awareness of the potential in that relationship
Joe Rospars, Chief Digital Strategist, Obama for America
Les tendances de fond du Big Data
10
La digitalisation massive des sphères économique, industrielle
et sociale ouvre le champ à de nouvelles approches dans les
domaines du marketing, de la finance et de l’industrie.
L’enjeu pour les Directions Générales et les Directions
Opérationnelles est de maîtriser cette opportunité pour faire
face aux changements profonds des marchés et anticiper les
évolutions des attentes des clients, des usages, des processus
et des infrastructures.
La Data Science ou l’art de maîtriser le Big Data tend à
supplanter son aspect technologique, de part son importante
stratégique.
Le Big Data et la Data Science redéfinissent profondément les
relations entre les métiers, la statistique et la technologie.
Digitalisation des
relations sociales
Marketing
Entreprise
digitale
Finance
Usine digitaleIndustrie
Monétisation des
datas
TMT/Banque
• Création et développement de produits spécifiques autour des technologies Big Data
• Veille technologique et scientifique
• Recherche et développement en Data Science
• Quantmetry est un cabinet de conseil « pure player » de la Data Science et du Big Data
• Nous aidons les entreprises à créer de la valeur grâce à l’analyse de leurs données
• Nous sommes une équipe pluridisciplinaire de consultants, data scientists, experts Big Data
• Nous appuyons nos recommandations sur des modèles mathématiques et statistiques
Quantmetry : Big Data & Data Science
11
Quantmetry
12
Exemples de Projets data
13
• Marketing, ciblage
• Compteurs intelligents: prédiction de consommation d’électricité ou d’eau
• Identification des molécules les plus efficaces dans la chimiothérapie
contre le cancer du sein
• Prédiction d’occupation de station Vélib
• Optimisation des routes aériennes en fonction du trafic
• Prédiction de pannes sur des flottes automobiles
• Prédiction de sécheresse en utilisant les photos satellites
• Détection de fraude (sécurité sociale, assurance, impôts)
DataminingInterpretation
Actions
Modeling
Collection
Preparation
• Reporting
• Visualization
• Analysis
• Predictions
Data Science Process
Artificial intelligence
and neurons
Artificial intelligence (1956)
16
How to mimic the brain?
Build artificial intelligences able to think
and act like humans
• Information travels as electric signals
(spikes) along the dendrites and axon
• Neuron gets activated if electric signal is
higher than a threshold at the synapse
• Activation is more intense if the
frequency of the signal is high
McCulloch & Pitts, Rosenblatt (1950s) The perceptron
17
a 𝑥 = 𝑤1 𝑥1 + 𝑤2 𝑥2 + 𝑏
ℎ 𝑥 = 𝑔(𝑎 𝑥 )
Artifical neuron = a computational unit that makes a computation based on the
information it gets from other neurons
• 𝑥 = input vector (real valued)
electric signal
• 𝑤 = connection weights
excitation or inhibition of the neuron
• 𝑏 = neuron bias
simulates a threshold (in combination
with the weights)
• 𝑔 = activation function
Activation of the neuron
Activation functions
18
• Heaviside (perceptron):
𝑔 𝑎 =
1 if 𝑎 > 0
0 otherwise
• Linear function
𝑔 𝑎 = 𝑎
• Sigmoid
𝑔 𝑎 =
1
1 + exp −𝑎
• Tanh
𝑔 𝑎 =
𝑒 𝑎
− 𝑒−𝑎
𝑒 𝑎 + 𝑒−𝑎
Linear function:
• Does not introduce non linearity
• Does not bound the output
-> Not very interesting
Heaviside function:
• A little too harsh -> smoother activation is
preferable to extract valuable information
Sigmoid and tanh are commonly used (with
softmax)
Capacity of a neuron: how much can it do?
19
Sigmoid function
𝑔 𝑎 =
1
1 + exp −𝑎
Output ∈ [𝟎, 𝟏]
h x = p(y = 1|x)
Interpretation: the output is the probability
to belong to a given class (y = 0 or 1)
x1
x2
A neuron can solve linearly separable problems
Boolean functions
20
0 1
1
0 0 0
1 0
x1
x2
0 1
1
0 0 1
0 0
x1
x2
0 1
1
0 0 1
1 1
x1
x2
0 1
1
0 0 0
0 1
x1
x2
OR (𝑥1, 𝑥2) AND (𝑥1, 𝑥2)
AND (𝑥1, 𝑥2) AND (𝑥1, 𝑥2)
The XOR affair (1969)
21
Minsky and Papert (1969), Perceptrons: an introduction to computational geometry
XOR (𝑥1, 𝑥2) impossible
with only two layers
0 1
1
0 0 1
1 0
x1
x2
OK with three layers
An intermediate
layer builds
a better
representation
(with AND
functions)
Multilayer neural networks
Can they recognize objects?
Can they build their own representations like humans?
Towards a multiply distributed representation
23
Multiple layers neural networks
Each layer is a distributed representation.
The units are not mutually exclusive
(neurons can all be activated
simultaneously).
Different from a partition of the input
(the input belong to a specific cluster)
The treachery of images
24
The CAR concept
• An infinity of possible images!
• A high-level abstraction represented by
pixels
• Many problems:
– Orientation
– Perspective
– Reflection
– Irrelevant background
A CAR detector
Built a CAR detector: decompose the problem
• What are the different shapes?
• How are they combined?
• Orientation?
• Perspective
Pixels
Low level
abstraction
Intermediate
level
abstraction
…
High level
abstraction
Car
Spectrum of machine learning tasks (Hinton’s view)
Statistics
• Low-dimensional data
(<100 dimensions)
• Lots of noise in the data
• Little structure that can be
captured by a rather simple model
Main problematic:
Separate true structure from noise
Artificial Intelligence
• High-dimensional data
(>100 dimensions)
• Noise should not be a problem
• Huge amount of structure, very
complicated
Main problematic:
Represent the complicated
structure so that it can be learned
Training a NN / Learning
27
Training / learning is an optimization problem
M examples with n features
𝑥1, 𝑥2, … , 𝑥 𝑛
Two class 𝟎, 𝟏 classification
Prediction
1 if f x = p y = 1 x > 0.5
0 otherwise
• Classification error is not a smooth function
• Better optimize a smooth upper bound substitute: the loss function
Learning algorithm
28
Backpropagation algorithm
• Invented in 1969 (Bryson and Ho)
• Independently re-discovered in the mid-1980s by several groups
• 1989: First successful application to deep neural network (LeCun) – Recognition of hand-written digits
1. Initialize the parameters 𝜃 = (𝑤, 𝑏)
2. For i = 1…M iterations (examples)
• Each training example 𝑥 𝑡
, 𝑦 𝑡
∆= −𝛻𝜃l f 𝑥 𝑡
; 𝜃 , 𝑦 𝑡
− 𝜆𝛻𝜃 𝛺 𝜃
𝜃= 𝜃+𝛼∆
• The gradient tells in what direction the biggest decrease in the loss function is, i.e. how
can we change the parameters to reduce the loss.
• 𝛼: hyperparameter = learning rate
Important things: a good loss function, an initialization method, an efficient way of computing the gradient
many times (for each example!)
Training a NN / Learning
29
Then backpropagate -> modify (w,b) for each layer
For each training example, do forward propagation -> get f(x)
Many tricks for training a NN
30
• Mini-batch learning
• Regularization: the bias and variance
• How much variance in the correct model: 𝜆 ≫ 0
• Bias: how far away from the true model are we? 𝜆 ∼ 0
• Tuning hyperparameter for a better generalization: do not optimize too
much
Early stopping
Deep learning
Why is it so difficult?
Usually better to use only 1 layer! Why?
• Underfitting situation: a very difficult optimization problem
We would do better with a better optimization procedure.
• Saturated units -> vanishing gradient -> updates are difficult
(close to 0)
• But saturation corresponds to the nonlinearity of NN, their
interesting part
• Overfitting situation: too many layers -> too fancy model
• Not enough data!!!! -> But with big data, things tend to improve
Better optimization
Better initialization and better regularization
2006: The Breakthrough
Before 2006: training deep neural networks was unsuccessful!
(except for CNN)
2006: 3 seminal papers
• Hinton, Osindero, and Teh,
A Fast Learning Algorithm for Deep Belief Nets
Neural Computation, 2006
• Bengio, Lamblin, Popovici, Larochelle,
Greedy Layer-Wise Training of Deep Networks
Advances in neural information processing systems, 2007
• Ranzato, Poultney, Chopra, LeCun,
Efficient Learning of Sparse Representations with an Energy-Based Model
Advances in neural information processing systems, 2006
The main point: greedy learning
Find the good representation: do it using unsupervised training -> let the neural
networt learn by itself!!
• Recognize the difference between a character and a random image
-> try to understand instead of copying -> less overfitting and improved
generalization
• Unsupervised pretraining: Train layer by layer (greedy learning) -> local extraction of
information -> the previous layer is seen as raw input representing features
• Each layer is able to find the most common features in the training inputs (more
common than random).
Once a good representation has been found at each level: it can be used to initialize
and successfully train a deep neural network with usual supervised gradient-base
optimization (backpropagation)
MNIST
35
Result of pretraining
36
Larochelle, Bengio, Louradour, Lamblin JMLR (2009)
Many unsupervised learning techniques
• Restricted Boltzmann machines
• Stack denoising autoencoders
• Semi-supervised embeddings
• Stacked kernel PCA
• Stacked independent subspace analysis
• …
Partially solves the problem of unlabelled data
• Pre-train on unlabelled data
• Fine-tuning using labelled data (supervised learning)
Pretraining does help deep learning
38
Why does unsupervised pre-
training help deep learning?
Erhan, Courville, Manzagol,
Bengio, 2011
Google Brain
39
2012: Google’s Large Scale Deep Learning Experiments
• an artificial neural network
• computation spread across 16,000 CPUs
• models with more than 1 billion connections
The next steps
40
Deep learning is good for:
• Automatic speech recognition
• Image recognition
• Natural language processing
• How well can deep learning be adapted to distributed systems (Big Data)?
• Learning Online?
• Application to other problems?
• Time series (consumption prediction)
• Scoring (churn prediction, marketing)
• Application to clustering
• How much more data?
Questions?
@heloisenonne
www.quantmetry.com

Contenu connexe

Tendances

Scalable Learning in Computer Vision
Scalable Learning in Computer VisionScalable Learning in Computer Vision
Scalable Learning in Computer Vision
butest
 
Dr. Erin LeDell, Machine Learning Scientist, H2O.ai at MLconf SEA - 5/20/16
Dr. Erin LeDell, Machine Learning Scientist, H2O.ai at MLconf SEA - 5/20/16Dr. Erin LeDell, Machine Learning Scientist, H2O.ai at MLconf SEA - 5/20/16
Dr. Erin LeDell, Machine Learning Scientist, H2O.ai at MLconf SEA - 5/20/16
MLconf
 
Le Song, Assistant Professor, College of Computing, Georgia Institute of Tech...
Le Song, Assistant Professor, College of Computing, Georgia Institute of Tech...Le Song, Assistant Professor, College of Computing, Georgia Institute of Tech...
Le Song, Assistant Professor, College of Computing, Georgia Institute of Tech...
MLconf
 

Tendances (20)

Squeezing Deep Learning Into Mobile Phones
Squeezing Deep Learning Into Mobile PhonesSqueezing Deep Learning Into Mobile Phones
Squeezing Deep Learning Into Mobile Phones
 
Applying your Convolutional Neural Networks
Applying your Convolutional Neural NetworksApplying your Convolutional Neural Networks
Applying your Convolutional Neural Networks
 
Capitalico / Chart Pattern Matching in Financial Trading Using RNN
Capitalico / Chart Pattern Matching in Financial Trading Using RNNCapitalico / Chart Pattern Matching in Financial Trading Using RNN
Capitalico / Chart Pattern Matching in Financial Trading Using RNN
 
Scalable Learning in Computer Vision
Scalable Learning in Computer VisionScalable Learning in Computer Vision
Scalable Learning in Computer Vision
 
Dr. Erin LeDell, Machine Learning Scientist, H2O.ai at MLconf SEA - 5/20/16
Dr. Erin LeDell, Machine Learning Scientist, H2O.ai at MLconf SEA - 5/20/16Dr. Erin LeDell, Machine Learning Scientist, H2O.ai at MLconf SEA - 5/20/16
Dr. Erin LeDell, Machine Learning Scientist, H2O.ai at MLconf SEA - 5/20/16
 
Daniel Shank, Data Scientist, Talla at MLconf SF 2016
Daniel Shank, Data Scientist, Talla at MLconf SF 2016Daniel Shank, Data Scientist, Talla at MLconf SF 2016
Daniel Shank, Data Scientist, Talla at MLconf SF 2016
 
Deep learning with tensorflow
Deep learning with tensorflowDeep learning with tensorflow
Deep learning with tensorflow
 
The deep learning tour - Q1 2017
The deep learning tour - Q1 2017 The deep learning tour - Q1 2017
The deep learning tour - Q1 2017
 
Smaller and Easier: Machine Learning on Embedded Things
Smaller and Easier: Machine Learning on Embedded ThingsSmaller and Easier: Machine Learning on Embedded Things
Smaller and Easier: Machine Learning on Embedded Things
 
TensorFlow
TensorFlowTensorFlow
TensorFlow
 
Introduction to Recurrent Neural Network
Introduction to Recurrent Neural NetworkIntroduction to Recurrent Neural Network
Introduction to Recurrent Neural Network
 
Google Big Data Expo
Google Big Data ExpoGoogle Big Data Expo
Google Big Data Expo
 
Machine learning and climate and weather research
Machine learning and climate and weather researchMachine learning and climate and weather research
Machine learning and climate and weather research
 
Melanie Warrick, Deep Learning Engineer, Skymind.io at MLconf SF - 11/13/15
Melanie Warrick, Deep Learning Engineer, Skymind.io at MLconf SF - 11/13/15Melanie Warrick, Deep Learning Engineer, Skymind.io at MLconf SF - 11/13/15
Melanie Warrick, Deep Learning Engineer, Skymind.io at MLconf SF - 11/13/15
 
Deep learning at nmc devin jones
Deep learning at nmc devin jones Deep learning at nmc devin jones
Deep learning at nmc devin jones
 
Anima Anandkumar at AI Frontiers : Modern ML : Deep, distributed, Multi-dimen...
Anima Anandkumar at AI Frontiers : Modern ML : Deep, distributed, Multi-dimen...Anima Anandkumar at AI Frontiers : Modern ML : Deep, distributed, Multi-dimen...
Anima Anandkumar at AI Frontiers : Modern ML : Deep, distributed, Multi-dimen...
 
Le Song, Assistant Professor, College of Computing, Georgia Institute of Tech...
Le Song, Assistant Professor, College of Computing, Georgia Institute of Tech...Le Song, Assistant Professor, College of Computing, Georgia Institute of Tech...
Le Song, Assistant Professor, College of Computing, Georgia Institute of Tech...
 
Array computing and the evolution of SciPy, NumPy, and PyData
Array computing and the evolution of SciPy, NumPy, and PyDataArray computing and the evolution of SciPy, NumPy, and PyData
Array computing and the evolution of SciPy, NumPy, and PyData
 
“An Introduction to Data Augmentation Techniques in ML Frameworks,” a Present...
“An Introduction to Data Augmentation Techniques in ML Frameworks,” a Present...“An Introduction to Data Augmentation Techniques in ML Frameworks,” a Present...
“An Introduction to Data Augmentation Techniques in ML Frameworks,” a Present...
 
李育杰/The Growth of a Data Scientist
李育杰/The Growth of a Data Scientist李育杰/The Growth of a Data Scientist
李育杰/The Growth of a Data Scientist
 

En vedette

Terascale Learning
Terascale LearningTerascale Learning
Terascale Learning
pauldix
 

En vedette (20)

Online learning, Vowpal Wabbit and Hadoop
Online learning, Vowpal Wabbit and HadoopOnline learning, Vowpal Wabbit and Hadoop
Online learning, Vowpal Wabbit and Hadoop
 
Distributed machine learning examples
Distributed machine learning examplesDistributed machine learning examples
Distributed machine learning examples
 
Terascale Learning
Terascale LearningTerascale Learning
Terascale Learning
 
Challenges in Large Scale Machine Learning
Challenges in Large Scale  Machine LearningChallenges in Large Scale  Machine Learning
Challenges in Large Scale Machine Learning
 
Présentation Big Data et REX Hadoop
Présentation Big Data et REX HadoopPrésentation Big Data et REX Hadoop
Présentation Big Data et REX Hadoop
 
Paris Spark Meetup (Feb2015) ccarbone : SPARK Streaming vs Storm / MLLib / Ne...
Paris Spark Meetup (Feb2015) ccarbone : SPARK Streaming vs Storm / MLLib / Ne...Paris Spark Meetup (Feb2015) ccarbone : SPARK Streaming vs Storm / MLLib / Ne...
Paris Spark Meetup (Feb2015) ccarbone : SPARK Streaming vs Storm / MLLib / Ne...
 
Diffusion MRI, Tractography,and Connectivity: what machine learning can do?
Diffusion MRI, Tractography,and Connectivity: what machine learning can do?Diffusion MRI, Tractography,and Connectivity: what machine learning can do?
Diffusion MRI, Tractography,and Connectivity: what machine learning can do?
 
Distributed machine learning
Distributed machine learningDistributed machine learning
Distributed machine learning
 
Cassandra spark connector
Cassandra spark connectorCassandra spark connector
Cassandra spark connector
 
H2O World - Consensus Optimization and Machine Learning - Stephen Boyd
H2O World - Consensus Optimization and Machine Learning - Stephen BoydH2O World - Consensus Optimization and Machine Learning - Stephen Boyd
H2O World - Consensus Optimization and Machine Learning - Stephen Boyd
 
NIPS2013読み会: More Effective Distributed ML via a Stale Synchronous Parallel P...
NIPS2013読み会: More Effective Distributed ML via a Stale Synchronous Parallel P...NIPS2013読み会: More Effective Distributed ML via a Stale Synchronous Parallel P...
NIPS2013読み会: More Effective Distributed ML via a Stale Synchronous Parallel P...
 
Lessons from 2MM machine learning models
Lessons from 2MM machine learning modelsLessons from 2MM machine learning models
Lessons from 2MM machine learning models
 
Deep Water - Bringing Tensorflow, Caffe, Mxnet to H2O
Deep Water - Bringing Tensorflow, Caffe, Mxnet to H2ODeep Water - Bringing Tensorflow, Caffe, Mxnet to H2O
Deep Water - Bringing Tensorflow, Caffe, Mxnet to H2O
 
June Spark meetup : search as recommandation
June Spark meetup : search as recommandationJune Spark meetup : search as recommandation
June Spark meetup : search as recommandation
 
Paris Spark meetup : Extension de Spark (Tachyon / Spark JobServer) par jlamiel
Paris Spark meetup : Extension de Spark (Tachyon / Spark JobServer) par jlamielParis Spark meetup : Extension de Spark (Tachyon / Spark JobServer) par jlamiel
Paris Spark meetup : Extension de Spark (Tachyon / Spark JobServer) par jlamiel
 
Spark ML par Xebia (Spark Meetup du 11/06/2015)
Spark ML par Xebia (Spark Meetup du 11/06/2015)Spark ML par Xebia (Spark Meetup du 11/06/2015)
Spark ML par Xebia (Spark Meetup du 11/06/2015)
 
Deep neural networks
Deep neural networksDeep neural networks
Deep neural networks
 
Spark dataframe
Spark dataframeSpark dataframe
Spark dataframe
 
Big data ppt
Big data pptBig data ppt
Big data ppt
 
What is Big Data?
What is Big Data?What is Big Data?
What is Big Data?
 

Similaire à Neural Networks and Deep Learning for Physicists

Similaire à Neural Networks and Deep Learning for Physicists (20)

Computer Design Concepts for Machine Learning
Computer Design Concepts for Machine LearningComputer Design Concepts for Machine Learning
Computer Design Concepts for Machine Learning
 
machine learning in the age of big data: new approaches and business applicat...
machine learning in the age of big data: new approaches and business applicat...machine learning in the age of big data: new approaches and business applicat...
machine learning in the age of big data: new approaches and business applicat...
 
Deeplearning in finance
Deeplearning in financeDeeplearning in finance
Deeplearning in finance
 
20181212 ibm aot
20181212 ibm aot20181212 ibm aot
20181212 ibm aot
 
Deep learning: Cutting through the Myths and Hype
Deep learning: Cutting through the Myths and HypeDeep learning: Cutting through the Myths and Hype
Deep learning: Cutting through the Myths and Hype
 
Ml ppt at
Ml ppt atMl ppt at
Ml ppt at
 
Deep learning and computer vision
Deep learning and computer visionDeep learning and computer vision
Deep learning and computer vision
 
06-01 Machine Learning and Linear Regression.pptx
06-01 Machine Learning and Linear Regression.pptx06-01 Machine Learning and Linear Regression.pptx
06-01 Machine Learning and Linear Regression.pptx
 
Camp IT: Making the World More Efficient Using AI & Machine Learning
Camp IT: Making the World More Efficient Using AI & Machine LearningCamp IT: Making the World More Efficient Using AI & Machine Learning
Camp IT: Making the World More Efficient Using AI & Machine Learning
 
Big Data & Machine Learning - TDC2013 São Paulo - 12/0713
Big Data & Machine Learning - TDC2013 São Paulo - 12/0713Big Data & Machine Learning - TDC2013 São Paulo - 12/0713
Big Data & Machine Learning - TDC2013 São Paulo - 12/0713
 
[243] turning data into value
[243] turning data into value[243] turning data into value
[243] turning data into value
 
TensorFlow London: Cutting edge generative models
TensorFlow London: Cutting edge generative modelsTensorFlow London: Cutting edge generative models
TensorFlow London: Cutting edge generative models
 
Big Data & Machine Learning - TDC2013 Sao Paulo
Big Data & Machine Learning - TDC2013 Sao PauloBig Data & Machine Learning - TDC2013 Sao Paulo
Big Data & Machine Learning - TDC2013 Sao Paulo
 
Introduction to Machine Learning
Introduction to Machine LearningIntroduction to Machine Learning
Introduction to Machine Learning
 
AI Presentation 1
AI Presentation 1AI Presentation 1
AI Presentation 1
 
Ai demystified (dbe, south campus)
Ai  demystified (dbe, south campus)Ai  demystified (dbe, south campus)
Ai demystified (dbe, south campus)
 
Deep Learning Training at Intel
Deep Learning Training at IntelDeep Learning Training at Intel
Deep Learning Training at Intel
 
A historical introduction to deep learning: hardware, data, and tricks
A historical introduction to deep learning: hardware, data, and tricksA historical introduction to deep learning: hardware, data, and tricks
A historical introduction to deep learning: hardware, data, and tricks
 
Useful Techniques in Artificial Intelligence
Useful Techniques in Artificial IntelligenceUseful Techniques in Artificial Intelligence
Useful Techniques in Artificial Intelligence
 
Deep learning tutorial 9/2019
Deep learning tutorial 9/2019Deep learning tutorial 9/2019
Deep learning tutorial 9/2019
 

Dernier

Call Girls Indiranagar Just Call 👗 7737669865 👗 Top Class Call Girl Service B...
Call Girls Indiranagar Just Call 👗 7737669865 👗 Top Class Call Girl Service B...Call Girls Indiranagar Just Call 👗 7737669865 👗 Top Class Call Girl Service B...
Call Girls Indiranagar Just Call 👗 7737669865 👗 Top Class Call Girl Service B...
amitlee9823
 
Call Girls Bannerghatta Road Just Call 👗 7737669865 👗 Top Class Call Girl Ser...
Call Girls Bannerghatta Road Just Call 👗 7737669865 👗 Top Class Call Girl Ser...Call Girls Bannerghatta Road Just Call 👗 7737669865 👗 Top Class Call Girl Ser...
Call Girls Bannerghatta Road Just Call 👗 7737669865 👗 Top Class Call Girl Ser...
amitlee9823
 
Just Call Vip call girls kakinada Escorts ☎️9352988975 Two shot with one girl...
Just Call Vip call girls kakinada Escorts ☎️9352988975 Two shot with one girl...Just Call Vip call girls kakinada Escorts ☎️9352988975 Two shot with one girl...
Just Call Vip call girls kakinada Escorts ☎️9352988975 Two shot with one girl...
gajnagarg
 
Call Girls In Hsr Layout ☎ 7737669865 🥵 Book Your One night Stand
Call Girls In Hsr Layout ☎ 7737669865 🥵 Book Your One night StandCall Girls In Hsr Layout ☎ 7737669865 🥵 Book Your One night Stand
Call Girls In Hsr Layout ☎ 7737669865 🥵 Book Your One night Stand
amitlee9823
 
Just Call Vip call girls Erode Escorts ☎️9352988975 Two shot with one girl (E...
Just Call Vip call girls Erode Escorts ☎️9352988975 Two shot with one girl (E...Just Call Vip call girls Erode Escorts ☎️9352988975 Two shot with one girl (E...
Just Call Vip call girls Erode Escorts ☎️9352988975 Two shot with one girl (E...
gajnagarg
 
Vip Mumbai Call Girls Thane West Call On 9920725232 With Body to body massage...
Vip Mumbai Call Girls Thane West Call On 9920725232 With Body to body massage...Vip Mumbai Call Girls Thane West Call On 9920725232 With Body to body massage...
Vip Mumbai Call Girls Thane West Call On 9920725232 With Body to body massage...
amitlee9823
 
Vip Mumbai Call Girls Marol Naka Call On 9920725232 With Body to body massage...
Vip Mumbai Call Girls Marol Naka Call On 9920725232 With Body to body massage...Vip Mumbai Call Girls Marol Naka Call On 9920725232 With Body to body massage...
Vip Mumbai Call Girls Marol Naka Call On 9920725232 With Body to body massage...
amitlee9823
 
Abortion pills in Jeddah | +966572737505 | Get Cytotec
Abortion pills in Jeddah | +966572737505 | Get CytotecAbortion pills in Jeddah | +966572737505 | Get Cytotec
Abortion pills in Jeddah | +966572737505 | Get Cytotec
Abortion pills in Riyadh +966572737505 get cytotec
 
➥🔝 7737669865 🔝▻ Bangalore Call-girls in Women Seeking Men 🔝Bangalore🔝 Esc...
➥🔝 7737669865 🔝▻ Bangalore Call-girls in Women Seeking Men  🔝Bangalore🔝   Esc...➥🔝 7737669865 🔝▻ Bangalore Call-girls in Women Seeking Men  🔝Bangalore🔝   Esc...
➥🔝 7737669865 🔝▻ Bangalore Call-girls in Women Seeking Men 🔝Bangalore🔝 Esc...
amitlee9823
 
Junnasandra Call Girls: 🍓 7737669865 🍓 High Profile Model Escorts | Bangalore...
Junnasandra Call Girls: 🍓 7737669865 🍓 High Profile Model Escorts | Bangalore...Junnasandra Call Girls: 🍓 7737669865 🍓 High Profile Model Escorts | Bangalore...
Junnasandra Call Girls: 🍓 7737669865 🍓 High Profile Model Escorts | Bangalore...
amitlee9823
 
Just Call Vip call girls Mysore Escorts ☎️9352988975 Two shot with one girl (...
Just Call Vip call girls Mysore Escorts ☎️9352988975 Two shot with one girl (...Just Call Vip call girls Mysore Escorts ☎️9352988975 Two shot with one girl (...
Just Call Vip call girls Mysore Escorts ☎️9352988975 Two shot with one girl (...
gajnagarg
 
Call Girls Hsr Layout Just Call 👗 7737669865 👗 Top Class Call Girl Service Ba...
Call Girls Hsr Layout Just Call 👗 7737669865 👗 Top Class Call Girl Service Ba...Call Girls Hsr Layout Just Call 👗 7737669865 👗 Top Class Call Girl Service Ba...
Call Girls Hsr Layout Just Call 👗 7737669865 👗 Top Class Call Girl Service Ba...
amitlee9823
 
Call Girls In Doddaballapur Road ☎ 7737669865 🥵 Book Your One night Stand
Call Girls In Doddaballapur Road ☎ 7737669865 🥵 Book Your One night StandCall Girls In Doddaballapur Road ☎ 7737669865 🥵 Book Your One night Stand
Call Girls In Doddaballapur Road ☎ 7737669865 🥵 Book Your One night Stand
amitlee9823
 
Call Girls In Nandini Layout ☎ 7737669865 🥵 Book Your One night Stand
Call Girls In Nandini Layout ☎ 7737669865 🥵 Book Your One night StandCall Girls In Nandini Layout ☎ 7737669865 🥵 Book Your One night Stand
Call Girls In Nandini Layout ☎ 7737669865 🥵 Book Your One night Stand
amitlee9823
 
Abortion pills in Doha Qatar (+966572737505 ! Get Cytotec
Abortion pills in Doha Qatar (+966572737505 ! Get CytotecAbortion pills in Doha Qatar (+966572737505 ! Get Cytotec
Abortion pills in Doha Qatar (+966572737505 ! Get Cytotec
Abortion pills in Riyadh +966572737505 get cytotec
 

Dernier (20)

Call Girls Indiranagar Just Call 👗 7737669865 👗 Top Class Call Girl Service B...
Call Girls Indiranagar Just Call 👗 7737669865 👗 Top Class Call Girl Service B...Call Girls Indiranagar Just Call 👗 7737669865 👗 Top Class Call Girl Service B...
Call Girls Indiranagar Just Call 👗 7737669865 👗 Top Class Call Girl Service B...
 
Call Girls Bannerghatta Road Just Call 👗 7737669865 👗 Top Class Call Girl Ser...
Call Girls Bannerghatta Road Just Call 👗 7737669865 👗 Top Class Call Girl Ser...Call Girls Bannerghatta Road Just Call 👗 7737669865 👗 Top Class Call Girl Ser...
Call Girls Bannerghatta Road Just Call 👗 7737669865 👗 Top Class Call Girl Ser...
 
Just Call Vip call girls kakinada Escorts ☎️9352988975 Two shot with one girl...
Just Call Vip call girls kakinada Escorts ☎️9352988975 Two shot with one girl...Just Call Vip call girls kakinada Escorts ☎️9352988975 Two shot with one girl...
Just Call Vip call girls kakinada Escorts ☎️9352988975 Two shot with one girl...
 
Call Girls In Hsr Layout ☎ 7737669865 🥵 Book Your One night Stand
Call Girls In Hsr Layout ☎ 7737669865 🥵 Book Your One night StandCall Girls In Hsr Layout ☎ 7737669865 🥵 Book Your One night Stand
Call Girls In Hsr Layout ☎ 7737669865 🥵 Book Your One night Stand
 
(NEHA) Call Girls Katra Call Now 8617697112 Katra Escorts 24x7
(NEHA) Call Girls Katra Call Now 8617697112 Katra Escorts 24x7(NEHA) Call Girls Katra Call Now 8617697112 Katra Escorts 24x7
(NEHA) Call Girls Katra Call Now 8617697112 Katra Escorts 24x7
 
Discover Why Less is More in B2B Research
Discover Why Less is More in B2B ResearchDiscover Why Less is More in B2B Research
Discover Why Less is More in B2B Research
 
Just Call Vip call girls Erode Escorts ☎️9352988975 Two shot with one girl (E...
Just Call Vip call girls Erode Escorts ☎️9352988975 Two shot with one girl (E...Just Call Vip call girls Erode Escorts ☎️9352988975 Two shot with one girl (E...
Just Call Vip call girls Erode Escorts ☎️9352988975 Two shot with one girl (E...
 
Vip Mumbai Call Girls Thane West Call On 9920725232 With Body to body massage...
Vip Mumbai Call Girls Thane West Call On 9920725232 With Body to body massage...Vip Mumbai Call Girls Thane West Call On 9920725232 With Body to body massage...
Vip Mumbai Call Girls Thane West Call On 9920725232 With Body to body massage...
 
Vip Mumbai Call Girls Marol Naka Call On 9920725232 With Body to body massage...
Vip Mumbai Call Girls Marol Naka Call On 9920725232 With Body to body massage...Vip Mumbai Call Girls Marol Naka Call On 9920725232 With Body to body massage...
Vip Mumbai Call Girls Marol Naka Call On 9920725232 With Body to body massage...
 
Detecting Credit Card Fraud: A Machine Learning Approach
Detecting Credit Card Fraud: A Machine Learning ApproachDetecting Credit Card Fraud: A Machine Learning Approach
Detecting Credit Card Fraud: A Machine Learning Approach
 
Abortion pills in Jeddah | +966572737505 | Get Cytotec
Abortion pills in Jeddah | +966572737505 | Get CytotecAbortion pills in Jeddah | +966572737505 | Get Cytotec
Abortion pills in Jeddah | +966572737505 | Get Cytotec
 
➥🔝 7737669865 🔝▻ Bangalore Call-girls in Women Seeking Men 🔝Bangalore🔝 Esc...
➥🔝 7737669865 🔝▻ Bangalore Call-girls in Women Seeking Men  🔝Bangalore🔝   Esc...➥🔝 7737669865 🔝▻ Bangalore Call-girls in Women Seeking Men  🔝Bangalore🔝   Esc...
➥🔝 7737669865 🔝▻ Bangalore Call-girls in Women Seeking Men 🔝Bangalore🔝 Esc...
 
Junnasandra Call Girls: 🍓 7737669865 🍓 High Profile Model Escorts | Bangalore...
Junnasandra Call Girls: 🍓 7737669865 🍓 High Profile Model Escorts | Bangalore...Junnasandra Call Girls: 🍓 7737669865 🍓 High Profile Model Escorts | Bangalore...
Junnasandra Call Girls: 🍓 7737669865 🍓 High Profile Model Escorts | Bangalore...
 
Just Call Vip call girls Mysore Escorts ☎️9352988975 Two shot with one girl (...
Just Call Vip call girls Mysore Escorts ☎️9352988975 Two shot with one girl (...Just Call Vip call girls Mysore Escorts ☎️9352988975 Two shot with one girl (...
Just Call Vip call girls Mysore Escorts ☎️9352988975 Two shot with one girl (...
 
Call Girls Hsr Layout Just Call 👗 7737669865 👗 Top Class Call Girl Service Ba...
Call Girls Hsr Layout Just Call 👗 7737669865 👗 Top Class Call Girl Service Ba...Call Girls Hsr Layout Just Call 👗 7737669865 👗 Top Class Call Girl Service Ba...
Call Girls Hsr Layout Just Call 👗 7737669865 👗 Top Class Call Girl Service Ba...
 
Call Girls In Doddaballapur Road ☎ 7737669865 🥵 Book Your One night Stand
Call Girls In Doddaballapur Road ☎ 7737669865 🥵 Book Your One night StandCall Girls In Doddaballapur Road ☎ 7737669865 🥵 Book Your One night Stand
Call Girls In Doddaballapur Road ☎ 7737669865 🥵 Book Your One night Stand
 
Call Girls In Nandini Layout ☎ 7737669865 🥵 Book Your One night Stand
Call Girls In Nandini Layout ☎ 7737669865 🥵 Book Your One night StandCall Girls In Nandini Layout ☎ 7737669865 🥵 Book Your One night Stand
Call Girls In Nandini Layout ☎ 7737669865 🥵 Book Your One night Stand
 
Thane Call Girls 7091864438 Call Girls in Thane Escort service book now -
Thane Call Girls 7091864438 Call Girls in Thane Escort service book now -Thane Call Girls 7091864438 Call Girls in Thane Escort service book now -
Thane Call Girls 7091864438 Call Girls in Thane Escort service book now -
 
Abortion pills in Doha Qatar (+966572737505 ! Get Cytotec
Abortion pills in Doha Qatar (+966572737505 ! Get CytotecAbortion pills in Doha Qatar (+966572737505 ! Get Cytotec
Abortion pills in Doha Qatar (+966572737505 ! Get Cytotec
 
Aspirational Block Program Block Syaldey District - Almora
Aspirational Block Program Block Syaldey District - AlmoraAspirational Block Program Block Syaldey District - Almora
Aspirational Block Program Block Syaldey District - Almora
 

Neural Networks and Deep Learning for Physicists

  • 1. February 19th, 2015 Data Science Consulting Héloïse Nonne, Data Scientist Big Data & deep learning CINaM, Aix-Marseille University
  • 3. Big Data? Explosion of data size Falling cost of data storage Increase of computing power “Information is the oil of the 21st century, and analytics is the combustion engine.” Peter Sondergaard, Senior Vice President, Gartner Research
  • 4. The falling cost of data storage 1980 1990 2000 2014 300 000 $ 1 000 $ 100$ 0,1$ 1956 IBM 350 RAMAC Capacity: 3.75 MB Storage cost for 1 Go
  • 5. Data growing exponentially • Over 90% of all the data in the world was created in the past 2 years. • Now, every year, 2 ZB are generated 1 ZB (zettabyte) = 1 trillion GB • IDC (International Data Corporation) predicts a generation of 40 ZB in 2020 • Around 100 hours of video are uploaded to YouTube every minute • Today’s datacenters occupy an area of land equal in size to almost 6,000 football fields
  • 7. Two approaches to large databases Total failure rate = product of local failure rates Design for failure at software level Source; www.tomshardware.com High-Tech hardware • Roughly double the cost of commodity • Roughly 5% failure rate Commodity (≠ low end) hardware • Roughly half the cost • Roughly 10-15% failure rate
  • 8. Distribution algorithm: MapReduce Key principles of a DFS • Duplication of data • Distribution of data • Colocalization of treatments • Parallel treatments • Horizontal and vertical elasticity Hadoop Distributed File System (HDFS) / Computing Distribution of data over multiple servers
  • 9. Yes but, what for? Big Data is about having an understanding of what your relationship is with the people who are the most important to you and an awareness of the potential in that relationship Joe Rospars, Chief Digital Strategist, Obama for America
  • 10. Les tendances de fond du Big Data 10 La digitalisation massive des sphères économique, industrielle et sociale ouvre le champ à de nouvelles approches dans les domaines du marketing, de la finance et de l’industrie. L’enjeu pour les Directions Générales et les Directions Opérationnelles est de maîtriser cette opportunité pour faire face aux changements profonds des marchés et anticiper les évolutions des attentes des clients, des usages, des processus et des infrastructures. La Data Science ou l’art de maîtriser le Big Data tend à supplanter son aspect technologique, de part son importante stratégique. Le Big Data et la Data Science redéfinissent profondément les relations entre les métiers, la statistique et la technologie. Digitalisation des relations sociales Marketing Entreprise digitale Finance Usine digitaleIndustrie Monétisation des datas TMT/Banque
  • 11. • Création et développement de produits spécifiques autour des technologies Big Data • Veille technologique et scientifique • Recherche et développement en Data Science • Quantmetry est un cabinet de conseil « pure player » de la Data Science et du Big Data • Nous aidons les entreprises à créer de la valeur grâce à l’analyse de leurs données • Nous sommes une équipe pluridisciplinaire de consultants, data scientists, experts Big Data • Nous appuyons nos recommandations sur des modèles mathématiques et statistiques Quantmetry : Big Data & Data Science 11
  • 13. Exemples de Projets data 13 • Marketing, ciblage • Compteurs intelligents: prédiction de consommation d’électricité ou d’eau • Identification des molécules les plus efficaces dans la chimiothérapie contre le cancer du sein • Prédiction d’occupation de station Vélib • Optimisation des routes aériennes en fonction du trafic • Prédiction de pannes sur des flottes automobiles • Prédiction de sécheresse en utilisant les photos satellites • Détection de fraude (sécurité sociale, assurance, impôts)
  • 16. Artificial intelligence (1956) 16 How to mimic the brain? Build artificial intelligences able to think and act like humans • Information travels as electric signals (spikes) along the dendrites and axon • Neuron gets activated if electric signal is higher than a threshold at the synapse • Activation is more intense if the frequency of the signal is high
  • 17. McCulloch & Pitts, Rosenblatt (1950s) The perceptron 17 a 𝑥 = 𝑤1 𝑥1 + 𝑤2 𝑥2 + 𝑏 ℎ 𝑥 = 𝑔(𝑎 𝑥 ) Artifical neuron = a computational unit that makes a computation based on the information it gets from other neurons • 𝑥 = input vector (real valued) electric signal • 𝑤 = connection weights excitation or inhibition of the neuron • 𝑏 = neuron bias simulates a threshold (in combination with the weights) • 𝑔 = activation function Activation of the neuron
  • 18. Activation functions 18 • Heaviside (perceptron): 𝑔 𝑎 = 1 if 𝑎 > 0 0 otherwise • Linear function 𝑔 𝑎 = 𝑎 • Sigmoid 𝑔 𝑎 = 1 1 + exp −𝑎 • Tanh 𝑔 𝑎 = 𝑒 𝑎 − 𝑒−𝑎 𝑒 𝑎 + 𝑒−𝑎 Linear function: • Does not introduce non linearity • Does not bound the output -> Not very interesting Heaviside function: • A little too harsh -> smoother activation is preferable to extract valuable information Sigmoid and tanh are commonly used (with softmax)
  • 19. Capacity of a neuron: how much can it do? 19 Sigmoid function 𝑔 𝑎 = 1 1 + exp −𝑎 Output ∈ [𝟎, 𝟏] h x = p(y = 1|x) Interpretation: the output is the probability to belong to a given class (y = 0 or 1) x1 x2 A neuron can solve linearly separable problems
  • 20. Boolean functions 20 0 1 1 0 0 0 1 0 x1 x2 0 1 1 0 0 1 0 0 x1 x2 0 1 1 0 0 1 1 1 x1 x2 0 1 1 0 0 0 0 1 x1 x2 OR (𝑥1, 𝑥2) AND (𝑥1, 𝑥2) AND (𝑥1, 𝑥2) AND (𝑥1, 𝑥2)
  • 21. The XOR affair (1969) 21 Minsky and Papert (1969), Perceptrons: an introduction to computational geometry XOR (𝑥1, 𝑥2) impossible with only two layers 0 1 1 0 0 1 1 0 x1 x2 OK with three layers An intermediate layer builds a better representation (with AND functions)
  • 22. Multilayer neural networks Can they recognize objects? Can they build their own representations like humans?
  • 23. Towards a multiply distributed representation 23 Multiple layers neural networks Each layer is a distributed representation. The units are not mutually exclusive (neurons can all be activated simultaneously). Different from a partition of the input (the input belong to a specific cluster)
  • 24. The treachery of images 24 The CAR concept • An infinity of possible images! • A high-level abstraction represented by pixels • Many problems: – Orientation – Perspective – Reflection – Irrelevant background
  • 25. A CAR detector Built a CAR detector: decompose the problem • What are the different shapes? • How are they combined? • Orientation? • Perspective Pixels Low level abstraction Intermediate level abstraction … High level abstraction Car
  • 26. Spectrum of machine learning tasks (Hinton’s view) Statistics • Low-dimensional data (<100 dimensions) • Lots of noise in the data • Little structure that can be captured by a rather simple model Main problematic: Separate true structure from noise Artificial Intelligence • High-dimensional data (>100 dimensions) • Noise should not be a problem • Huge amount of structure, very complicated Main problematic: Represent the complicated structure so that it can be learned
  • 27. Training a NN / Learning 27 Training / learning is an optimization problem M examples with n features 𝑥1, 𝑥2, … , 𝑥 𝑛 Two class 𝟎, 𝟏 classification Prediction 1 if f x = p y = 1 x > 0.5 0 otherwise • Classification error is not a smooth function • Better optimize a smooth upper bound substitute: the loss function
  • 28. Learning algorithm 28 Backpropagation algorithm • Invented in 1969 (Bryson and Ho) • Independently re-discovered in the mid-1980s by several groups • 1989: First successful application to deep neural network (LeCun) – Recognition of hand-written digits 1. Initialize the parameters 𝜃 = (𝑤, 𝑏) 2. For i = 1…M iterations (examples) • Each training example 𝑥 𝑡 , 𝑦 𝑡 ∆= −𝛻𝜃l f 𝑥 𝑡 ; 𝜃 , 𝑦 𝑡 − 𝜆𝛻𝜃 𝛺 𝜃 𝜃= 𝜃+𝛼∆ • The gradient tells in what direction the biggest decrease in the loss function is, i.e. how can we change the parameters to reduce the loss. • 𝛼: hyperparameter = learning rate Important things: a good loss function, an initialization method, an efficient way of computing the gradient many times (for each example!)
  • 29. Training a NN / Learning 29 Then backpropagate -> modify (w,b) for each layer For each training example, do forward propagation -> get f(x)
  • 30. Many tricks for training a NN 30 • Mini-batch learning • Regularization: the bias and variance • How much variance in the correct model: 𝜆 ≫ 0 • Bias: how far away from the true model are we? 𝜆 ∼ 0 • Tuning hyperparameter for a better generalization: do not optimize too much Early stopping
  • 32. Why is it so difficult? Usually better to use only 1 layer! Why? • Underfitting situation: a very difficult optimization problem We would do better with a better optimization procedure. • Saturated units -> vanishing gradient -> updates are difficult (close to 0) • But saturation corresponds to the nonlinearity of NN, their interesting part • Overfitting situation: too many layers -> too fancy model • Not enough data!!!! -> But with big data, things tend to improve Better optimization Better initialization and better regularization
  • 33. 2006: The Breakthrough Before 2006: training deep neural networks was unsuccessful! (except for CNN) 2006: 3 seminal papers • Hinton, Osindero, and Teh, A Fast Learning Algorithm for Deep Belief Nets Neural Computation, 2006 • Bengio, Lamblin, Popovici, Larochelle, Greedy Layer-Wise Training of Deep Networks Advances in neural information processing systems, 2007 • Ranzato, Poultney, Chopra, LeCun, Efficient Learning of Sparse Representations with an Energy-Based Model Advances in neural information processing systems, 2006
  • 34. The main point: greedy learning Find the good representation: do it using unsupervised training -> let the neural networt learn by itself!! • Recognize the difference between a character and a random image -> try to understand instead of copying -> less overfitting and improved generalization • Unsupervised pretraining: Train layer by layer (greedy learning) -> local extraction of information -> the previous layer is seen as raw input representing features • Each layer is able to find the most common features in the training inputs (more common than random). Once a good representation has been found at each level: it can be used to initialize and successfully train a deep neural network with usual supervised gradient-base optimization (backpropagation)
  • 36. Result of pretraining 36 Larochelle, Bengio, Louradour, Lamblin JMLR (2009)
  • 37. Many unsupervised learning techniques • Restricted Boltzmann machines • Stack denoising autoencoders • Semi-supervised embeddings • Stacked kernel PCA • Stacked independent subspace analysis • … Partially solves the problem of unlabelled data • Pre-train on unlabelled data • Fine-tuning using labelled data (supervised learning)
  • 38. Pretraining does help deep learning 38 Why does unsupervised pre- training help deep learning? Erhan, Courville, Manzagol, Bengio, 2011
  • 39. Google Brain 39 2012: Google’s Large Scale Deep Learning Experiments • an artificial neural network • computation spread across 16,000 CPUs • models with more than 1 billion connections
  • 40. The next steps 40 Deep learning is good for: • Automatic speech recognition • Image recognition • Natural language processing • How well can deep learning be adapted to distributed systems (Big Data)? • Learning Online? • Application to other problems? • Time series (consumption prediction) • Scoring (churn prediction, marketing) • Application to clustering • How much more data?