Transcript A Practical Guide to Training Restricted Boltzmann Machines

Restricted Boltzmann Machines and
Deep Networks for Unsupervised Learning
Instituto Italiano di Tecnologia, Genova
June 7th, 2011
Loris Bazzani
University of Verona
Brief Intro
• Unsupervised Learning
• Learning features from
(visual) data
• Focus here on Restricted
Boltzmann Machines
2
Outline Presentation
–
–
–
–
Binary RBMs
Gaussian-binary RBMs
RBMs for Classification
Deep Belief Networks (DBNs)
Theor
y
• Restricted Boltzmann Machines (RBMs)
• RBMs for Modeling Natural Scenes [Ranzato, CVPR 2010]
• Learning Attentional Policies [Bazzani, ICML 2011]
Applications
• Learning Algorithms
Outline Presentation
–
–
–
–
Binary RBMs
Gaussian-binary RBMs
RBMs for Classification
Deep Belief Networks (DBNs)
Theor
y
• Restricted Boltzmann Machines (RBMs)
• RBMs for Modeling Natural Scenes [Ranzato, CVPR 2010]
• Learning Attentional Policies [Bazzani, ICML 2011]
Applications
• Learning Algorithms
Restricted Boltzmann Machines
• Bipartite Probabilistic Graphical Model
W: parameters governing the interactions
between visible and hidden units
• Property: ”given the hidden units, all of the visible units
become independent and given the visible units, all of the
hidden units become independent”
5
Binary RBMs
• We can sample from
• Use the expected value of the hidden units as
features:
6
Gaussian-binary RBMs
• Popular extension for modeling natural images
• Make the visible units conditionally Gaussian
given the hidden units
• Conditional distributions
7
RBMs for Classification
1) Feed the hidden representation into a
standard classifier (e.g., multinomial logistic
regression, SVM, random forest,…)
2) Embed the class into the visible units
and, the class vector will be sample from
8
Deep Belief Networks
• Goal: reach a high level of abstraction,
so that classification becomes simple
(e.g., linear)
• Multiple stacked RBMs
• Learning consists in greedy training each
level sequentially from the bottom
• Add fine-tuning with back-propagation
• Or a non-linear classifier can be used
• PB: how many layers?
9
Outline Presentation
–
–
–
–
Binary RBMs
Gaussian-binary RBMs
RBMs for Classification
Deep Belief Networks (DBNs)
Theor
y
• Restricted Boltzmann Machines (RBMs)
• RBMs for Modeling Natural Scenes [Ranzato, CVPR 2010]
• Learning Attentional Policies [Bazzani, ICML 2011]
Applications
• Learning Algorithms
How to Learn the Parameters
• Maximum Likelihood (ML) techniques
• No close-form solution for the maximization
• Problem: Partition function usually not
efficiently computable
• Solutions:
• Approximate ML
• Sacrifices convergence properties to make it
computationally feasible
• Alternatives: variational methods, max-margin learning, etc.
11
ML Problem
Marginalizing
Gradient:
Match the gradient of the free energy under the data
distribution with the gradient under the model distribution
12
Contrastive Divergence (1)
• It is just a gradient descent
• At each step, it contrasts the data distribution
with the model distribution
• E.g., binary RBM
13
Contrastive Divergence (2)
• Algorithm for binary RBMs:
14
Outline Presentation
–
–
–
–
Binary RBMs
Gaussian-binary RBMs
RBMs for Classification
Deep Belief Networks (DBNs)
Theor
y
• Restricted Boltzmann Machines (RBMs)
• RBMs for Modeling Natural Scenes [Ranzato, CVPR 2010]
• Learning Attentional Policies [Bazzani, ICML 2011]
Applications
• Learning Algorithms
Modeling Natural Images
• Motivations:
– Learning a generative model of natural images
– Extracting features that capture regularities
– Opposed to using engineered features
• RBM with two set of hidden units:
– One represents the pixel intensity
– Another one, the pair-wise dependencies
• Called Mean-Covariance RBM (mc-RBM)
• It is still a Gaussian-binary RBM
17
mc-RBM Model (1)
• Capture pair-wire interactions with:
• Sketch:
Covariance
hiddens
18
mc-RBM Model (2)
• Representation of mean pixel intensities:
• Conditional distributions:
19
mc-RBM Model (3)
• Final Energy term:
Regularization
• Free Energy formulation is also computable
• Learning with
– Stochastic gradient descent
– And, Contrastive Divergence
– Sampling using Hybrid Monte Carlo
20
Training Protocol for Recognition
•
•
•
•
Images are pre-processed by PCA whitening
Train the mc-RBM
Extract features with mc-RBM
Train a classifier for object recognition:
– Multinomial Logistic Classifier
21
Object Recognition on CIFAR 10
22
Outline Presentation
–
–
–
–
Binary RBMs
Gaussian-binary RBMs
RBMs for Classification
Deep Belief Networks (DBNs)
Theor
y
• Restricted Boltzmann Machines (RBMs)
• RBMs for Modeling Natural Scenes [Ranzato, CVPR 2010]
• Learning Attentional Policies [Bazzani, ICML 2011]
Applications
• Learning Algorithms
Where do you look at?
Original video source: http://gpu4vision.icg.tugraz.at/index.php?content=subsites/prost/prost.php
Goal
• Human tracking and recognition is amazingly
efficient and effective
• Large stream of data is filtered by attention
• We propose a model for tracking and recognition
that takes inspiration from human visual system
• Tracking and recognition of “something” that is
moving in the scene
• Accumulate gaze data
• Plan where to look at in the next future
25
Parallelism with Human Brain
26
Source image: http://www.waece.org/cd_morelia2006/ponencias/stoodley.htm
Sketch of the Model
Classifier
Multi-fixation RBM
(mc-)RBM
Policy Learning
27
Modularity
Learning
Online
• Offline Training
•
from moving “things” with multiple
saccades
Extract gaze data from
a training dataset
autoencoders, sparse coding, etc.
• Train the (mc-)RBM
• Train the multi-fixation RBM (3 random gazes)
SVM, random forest, etc.
• Train the multinomial logistic classifier
• Online Learning
other bandit techniques or Bayesian optimization
• Hedge algorithm for policy learning
28
Experiments (1)
• 10 synthetic video sequences with moving and
background digits (from MNIST dataset)
Tracking error in pixels
Classification accuracy
Code available at: http://www.lorisbazzani.info/code-datasets/rbm-tracking/
Experiments (2)
Dataset available at: http://seqam.rutgers.edu/softdata/facedata/facedata.html
Summary
•
•
•
•
•
Several RBMs models
How to train RBMs
Their extensions for classification
RBMs as block for deep architectures
They are useful for learning features from
images, without engineering them
• Taking inspiration from human learning, DBNs
have been used
32
References (1)
Learning attentional policies for tracking and recognition in video with deep networks, Loris Bazzani,
Nando de Freitas, Hugo Larochelle, Vittorio Murino, and Jo-Anne Ting, International Conference on
Machine Learning, 2011
Tutorial on Stochastic Approximation Algorithms for Training Restricted Boltzmann Machines and
Deep Belief Nets, Swersky and Bo Chen, Benjamin Marlin, and Nando de Freitas, Information
Theory and Applications (ITA) Workshop, 2010
Inductive Principles for Restricted Boltzmann Machine Learning, Benjamin Marlin, Kevin Swersky, Bo
Chen, and Nando de Freitas, AISTATS, 2010
Modeling Pixel Means and Covariances Using Factorized Third-Order Boltzmann, Marc'Aurelio Ranzato
and Geoffrey E. Hinton, IEEE Computer Society Conference on Computer Vision and Pattern
Recognition, 2010
Factored 3-Way Restricted Boltzmann Machines For Modeling Natural Images, Marc'Aurelio Ranzato,
Alex Krizhevsky and Geoffrey E. Hinton, International Conference on Artificial Intelligence and
Statistics, 2010
On Deep Generative Models with Applications to Recognition, Marc'Aurelio Ranzato, Joshua Susskind,
Volodymyr Mnih, and Geoffrey Hinton, IEEE Computer Society Conference on Computer Vision and
Pattern Recognition, 2011
Learning to combine foveal glimpses with a third-order Boltzmann machine, Hugo Larochelle and
Geoffrey E. Hinton, Neural Information Processing Systems, 2010
33
References (2)
Stacks of Convolutional Restricted Boltzmann Machines for Shift-Invariant Feature Learning,
Mohammad Norouzi, Mani Ranjbar, and Greg Mori, IEEE Computer Society Conference on
Computer Vision and Pattern Recognition,2009
Deconvolutional Networks, Matthew D. Zeiler, Dilip Krishnan, Graham W. Taylor, and Rob Fergus, IEEE
Computer Society Conference on Computer Vision and Pattern Recognition, 2010
Convolutional deep belief networks for scalable unsupervised learning of hierarchical representations,
Lee, Honglak, Grosse, Roger, Ranganath, Rajesh and Ng, Andrew, International Conference on
Machine Learning, 2009
A deep learning approach to machine transliteration, Deselaers, Thomas, Hasan, Savsa, Bender, Oliver
and Ney, Hermann, Proceedings of the Fourth Workshop on Statistical Machine Translation, 2009
Learning Multilevel Distributed Representations for High-dimensional Sequences, Sutskever, I. and
Hinton, G. E., Proceeding of the Eleventh International Conference on Artificial Intelligence and
Statistics, 2007
On Contrastive Divergence Learning, Miguel A. Carreira-Perpinan and Geoffrey E. Hinton, International
Conference on Artificial Intelligence and Statistics, 2005
Convolutional learning of spatio-temporal features, Taylor, Graham W., Fergus, Rob, LeCun, Yann and
Bregler, Christoph, Proceedings of the 11th European conference on Computer vision, 2010
A Practical Guide to Training Restricted Boltzmann Machines, Geoffrey E. Hinton, University of Toronto,
2010, TR2010-003
34