Reading Group on Deep Learning Session 4 Unsupervised Neural Networks

Size: px
Start display at page:

Download "Reading Group on Deep Learning Session 4 Unsupervised Neural Networks"

Transcription

1 Reading Group on Deep Learning Session 4 Unsupervised Neural Networks Jakob Verbeek & Daan Wynen Jakob Verbeek & Daan Wynen Unsupervised Neural Networks

2 Outline Autoencoders Restricted) Boltzmann Macines Deep Belief Networks Jakob Verbeek & Daan Wynen Unsupervised Neural Networks

3 Autoencoders Autoencoders Jakob Verbeek & Daan Wynen Unsupervised Neural Networks

4 Autoencoders Autoencoder Input Code Reconstruction Input x Input fx) gfx)) Code Reconstruction Reconstruction Lfx), y) Lx, gfx))) Lx, e.g. gfx))) MSE) Jakob Verbeek & Daan Wynen Unsupervised Neural Networks

5 Autoencoders Autoencoder Input Code Reconstruction Input x Input fx) gfx)) Code Reconstruction Reconstruction Lfx), y) Lx, gfx))) Lx, e.g. gfx))) MSE) Jakob Verbeek & Daan Wynen Unsupervised Neural Networks

6 Autoencoders Autoencoder Input Code Reconstruction Input x Input fx) gfx)) Code Reconstruction Reconstruction Lfx), y) Lx, gfx))) Lx, e.g. gfx))) MSE) Jakob Verbeek & Daan Wynen Unsupervised Neural Networks

7 Autoencoders Autoencoder Input Code Reconstruction Input x Input fx) gfx)) Code Reconstruction Reconstruction Lfx), y) Lx, gfx))) Lx, e.g. gfx))) MSE) Jakob Verbeek & Daan Wynen Unsupervised Neural Networks

8 Autoencoders Autoencoder Input Code Reconstruction Input x Input fx) gfx)) Code Reconstruction Reconstruction Lfx), y) Lx, gfx))) Lx, e.g. gfx))) MSE) Jakob Verbeek & Daan Wynen Unsupervised Neural Networks

9 Autoencoders Denoising Autoencoder Input x Corrupted Input ˆx Reconstruction gfx)) Jakob Verbeek & Daan Wynen Lx, gfx))) Lx, gfx))) Unsupervised Neural Networks

10 Autoencoders Denoising Autoencoder Input x Corrupted Input ˆx Reconstruction gfx)) Jakob Verbeek & Daan Wynen Lx, gfx))) Lx, gfx))) Unsupervised Neural Networks

11 Autoencoders Denoising Autoencoder Input x Corrupted Input ˆx Reconstruction gfx)) Jakob Verbeek & Daan Wynen Lx, gfx))) Lx, gfx))) Unsupervised Neural Networks

12 Autoencoders Sparse Autoencoder Lx, gfx))) + Ωfx)) Jakob Verbeek & Daan Wynen Unsupervised Neural Networks

13 Restricted) Boltzmann Macines Restricted) Boltzmann Macines Jakob Verbeek & Daan Wynen Unsupervised Neural Networks

14 Restricted) Boltzmann Macines Boltzmann Macine Binary units x P x) = exp Ex) Z Ex) = x Ux b x Jakob Verbeek & Daan Wynen Unsupervised Neural Networks

15 Restricted) Boltzmann Macines Boltzmann Macine Binary units v, exp Ev, ) P v, ) = Z Ev, ) = v Rv v W S b v c Jakob Verbeek & Daan Wynen Unsupervised Neural Networks

16 Restricted) Boltzmann Macines Restricted Boltzmann Macine Binary units v, exp Ev, ) P v, ) = Z Ev, ) = v Rv v W S b v c Jakob Verbeek & Daan Wynen Unsupervised Neural Networks

17 Restricted) Boltzmann Macines Slides by Honglak Lee: ttp://videolectures.net/deeplearning205_lee_ boltzmann_macines Jakob Verbeek & Daan Wynen Unsupervised Neural Networks

18 5 Restricted Boltzmann Macines RBMs) Representation Undirected bipartite grapical model v 0, D : observed visible) binary variables 0, N : idden binary variables. idden H) j visible V) = w T v) + 2 w 2 T v) + 3 w 3 T v) b T c T v i

19 6 Restricted Boltzmann Macines RBMs) Representation Undirected bipartite grapical model v 0, D : observed visible) binary variables 0, N : idden binary variables. idden H) 2 3 w w 2 w 3 visible V) = w T v) + 2 w 2 T v) + 3 w 3 T v) b T c T v i

20 Conditional Probabilities RBM wit binary-valued input data) 7 Given v, all te j are conditionally independent idden H) 2 j 3 w w 2 w 3 P v) can be used as features Given, all te v i are conditionally independent i v v 2 visible V)

21 RBMs wit real-valued input data Representation Undirected bipartite grapical model V: observed visible) real variables H: idden binary variables. idden H) j i visible V) 8 8

22 9 RBMs wit real-valued input data Given v, all te j are conditionally independent idden H) w 2 j w 2 3 w 3 P v) can be used as features i v v 2 visible V) Given, all te v i are conditionally independent

23 0 Inference Conditional Distribution: Pv ) or P v) Easy to compute see previous slides). Due to conditional independence, we can sample idden units in parallel given visible units & vice versa) Joint Distribution: Pv,) Requires Gibbs Sampling approximate) Initialize wit v 0 Sample 0 from P v 0 ) Repeat until convergence t=, ) { Sample v t from Pv t t ) Sample t from P v t ) } v

24 Training RBMs Maximum likeliood training Objective: Log-likeliood of te training data were Computing exact gradient intractable. Typically sampling-based approximation is used e.g., contrastive divergence). Usually optimized via stocastic gradient descent

25 2 Training RBMs Model: How can we find parameters θ tat maximize P θ v)? Data Distribution posterior of given v) Model Distribution We need to compute P v) and Pv,), and derivative of E w.r.t. parameters {W,b,c} P v): tractable see previous slides) Pv,): intractable Can approximate wit Gibbs sampling, but requires lots of iterations

26 Contrastive Divergence Approximation of te log-likeliood gradient. Replace te average over all possible inputs by samples 2. Run te MCMC cain Gibbs sampling) for only k steps starting from te observed example Initialize wit v 0 = v Sample 0 from P v 0 ) For t =,,k { Sample v t from Pv t t ) Sample t from P v t ) } 3

27 Maximum likeliood learning for RBM j j j j vi j 0 v i j i i i i t = 0 t = t = 2 t = infinity Equilibrium distribution Slide Credit: Geoff Hinton 4

28 Contrastive divergence to learn RBM v i j i j t = 0 t = data reconstruction i j 0 v i j Start wit a training vector on te visible units. Update all te idden units in parallel Update te all te visible units in parallel to get a reconstruction. Update te idden units again. Slide Credit: Geoff Hinton 5

29 6 Update rule: Putting togeter Training via stocastic gradient. Note, E W ij = i v j. Terefore, were v k is a sample from k-step CD Can derive similar update rule for biases b and c Mini-batc ~00 samples) are used to reduce te variance of te gradient estimate Implemented in ~0 lines of matlab code

30 Deep Belief Networks Deep Belief Networks Jakob Verbeek & Daan Wynen Unsupervised Neural Networks

31 Deep Belief Networks DBNs) Probabilistic generative model Wit deep arcitecture multiple layers) Unsupervised pre-training wit RBMs provides a good initialization of te model Teoretically justified as maximizing te lowerbound of te log-likeliood of te data Supervised fine-tuning Generative: Up-down algoritm [Hinton et al., 2006] Discriminative: backpropagation convert to NN) Related work: Deep Boltzmann Macine Salakutdinov and Hinton, 2009) 24

32 25 Deep Belief Networks DBN) 2 3 v Visible layer Hidden layers RBM Directed belief nets ), ) )... ) ),...,,, 2 l l l l l P P P P P v v 2 2

33 26 DBN structure v 2 3 ) 2 P ) v P ), 2 3 P ) v Q ) 2 Q ) ) P Q W 2 W 3 W j i i j i j i i sigm P ) W ' ). b j i i j i j i i sigm Q ) W ) b ), ) )... ) ),...,,, 2 l l l l l P P P P P v v 2 2 Hinton et al., 2006 approximate) inference Generative process

34 27 First step: DBN Greedy training Construct an RBM wit an input layer v and a idden layer Train te RBM Hinton et al., 2006

35 28 Second step: DBN Greedy training Stack anoter idden layer on top of te RBM to form a new RBM Fix W, sample from Q v) as input. Train as RBM. 2 W 2 W Hinton et al., 2006 Q v) W

36 29 Tird step: DBN Greedy training Continue to stack layers on top of te network, train it as previous step, wit sample sampled 2 from Q ) And so on Q 2 ) 3 W 2 W 3 Hinton et al., 2006 Q v) W

37 36 DBN and supervised fine-tuning Discriminative fine-tuning Initializing wit neural nets + backpropagation Maximizes log P Y X ) X: data Y: label) Generative fine-tuning Up-down algoritm Maximizes log P Y, X ) joint likeliood of data and labels) Hinton et al. used supervised + generative fine-tuning in teir Neural Computation paper. However, it is possible to use unsupervised + generative fine-tuning as well.

38 A model for digit recognition Te top two layers form an associative memory Te energy valleys ave names 2000 top-level neurons 0 label neurons 500 neurons Te model learns to generate combinations of labels and images. To perform recognition we start wit a neutral state of te label units and do an up-pass from te image followed by a few iterations of te top-level associative memory. ttp:// 500 neurons 28 x 28 pixel image Slide Credit: Geoff Hinton 37

39 Generative fine-tuning via Up-down algoritm After pre-training many layers of features, we can finetune te features to improve generation.. Do a stocastic bottom-up pass Adjust te top-down weigts to be good at reconstructing te feature activities in te layer below. 2. Do a few iterations of sampling in te top level RBM Adjust te weigts in te top-level RBM. 3. Do a stocastic top-down pass Adjust te bottom-up weigts to be good at reconstructing te feature activities in te layer above. ttp:// Slide Credit: Geoff Hinton 38

40 39 Generating sample from a DBN Want to sample from Sample using Gibbs sampling in te RBM Sample te lower layer from l ) i i P i ), ) )... ) ),...,,, 2 l l l l l P P P P P v v 2 2

41 Generating samples from DBN Hinton et al, A Fast Learning Algoritm for Deep Belief Nets,

42 Stacking of RBMs as Deep Neural Networks 43

43 44 Using Stacks of RBMs as Neural Networks Te feedforward approximate) inference of te DBN looks te same as te sigmoid deep neural networks Idea: use te DBN as an initialization of te deep neural network, and ten do fine-tuning wit back-propagation

44 DBN for classification Slide credit: Russ Salakutdinov 45

45 Deep Belief Networks Deep Boltzmann Macine Figure: from ttp:// Specialization of Boltzmann Macine Jakob Verbeek & Daan Wynen Unsupervised Neural Networks

46 Deep Belief Networks Deep Boltzmann Macine Figure: from ttp:// Specialization of Boltzmann Macine Also specialization of Restricted Boltzmann Macine! Jakob Verbeek & Daan Wynen Unsupervised Neural Networks

47 Deep Belief Networks DBM - Properties Allows for up-down interactions between layers Compared to DBNets, Q v) can be tigter to P v) Also makes inference and training arder MCMC across all layers... Jakob Verbeek & Daan Wynen Unsupervised Neural Networks

A graph contains a set of nodes (vertices) connected by links (edges or arcs)

A graph contains a set of nodes (vertices) connected by links (edges or arcs) BOLTZMANN MACHINES Generative Models Graphical Models A graph contains a set of nodes (vertices) connected by links (edges or arcs) In a probabilistic graphical model, each node represents a random variable,

More information

Deep unsupervised learning

Deep unsupervised learning Deep unsupervised learning Advanced data-mining Yongdai Kim Department of Statistics, Seoul National University, South Korea Unsupervised learning In machine learning, there are 3 kinds of learning paradigm.

More information

Greedy Layer-Wise Training of Deep Networks

Greedy Layer-Wise Training of Deep Networks Greedy Layer-Wise Training of Deep Networks Yoshua Bengio, Pascal Lamblin, Dan Popovici, Hugo Larochelle NIPS 2007 Presented by Ahmed Hefny Story so far Deep neural nets are more expressive: Can learn

More information

UNSUPERVISED LEARNING

UNSUPERVISED LEARNING UNSUPERVISED LEARNING Topics Layer-wise (unsupervised) pre-training Restricted Boltzmann Machines Auto-encoders LAYER-WISE (UNSUPERVISED) PRE-TRAINING Breakthrough in 2006 Layer-wise (unsupervised) pre-training

More information

The Origin of Deep Learning. Lili Mou Jan, 2015

The Origin of Deep Learning. Lili Mou Jan, 2015 The Origin of Deep Learning Lili Mou Jan, 2015 Acknowledgment Most of the materials come from G. E. Hinton s online course. Outline Introduction Preliminary Boltzmann Machines and RBMs Deep Belief Nets

More information

Deep Belief Network Training Improvement Using Elite Samples Minimizing Free Energy

Deep Belief Network Training Improvement Using Elite Samples Minimizing Free Energy Deep Belief Network Training Improvement Using Elite Samples Minimizing Free Energy Moammad Ali Keyvanrad a, Moammad Medi Homayounpour a a Laboratory for Intelligent Multimedia Processing (LIMP), Computer

More information

Lecture 16 Deep Neural Generative Models

Lecture 16 Deep Neural Generative Models Lecture 16 Deep Neural Generative Models CMSC 35246: Deep Learning Shubhendu Trivedi & Risi Kondor University of Chicago May 22, 2017 Approach so far: We have considered simple models and then constructed

More information

Deep Learning Srihari. Deep Belief Nets. Sargur N. Srihari

Deep Learning Srihari. Deep Belief Nets. Sargur N. Srihari Deep Belief Nets Sargur N. Srihari srihari@cedar.buffalo.edu Topics 1. Boltzmann machines 2. Restricted Boltzmann machines 3. Deep Belief Networks 4. Deep Boltzmann machines 5. Boltzmann machines for continuous

More information

Knowledge Extraction from DBNs for Images

Knowledge Extraction from DBNs for Images Knowledge Extraction from DBNs for Images Son N. Tran and Artur d Avila Garcez Department of Computer Science City University London Contents 1 Introduction 2 Knowledge Extraction from DBNs 3 Experimental

More information

Learning to Disentangle Factors of Variation with Manifold Learning

Learning to Disentangle Factors of Variation with Manifold Learning Learning to Disentangle Factors of Variation with Manifold Learning Scott Reed Kihyuk Sohn Yuting Zhang Honglak Lee University of Michigan, Department of Electrical Engineering and Computer Science 08

More information

How to do backpropagation in a brain

How to do backpropagation in a brain How to do backpropagation in a brain Geoffrey Hinton Canadian Institute for Advanced Research & University of Toronto & Google Inc. Prelude I will start with three slides explaining a popular type of deep

More information

Deep Boltzmann Machines

Deep Boltzmann Machines Deep Boltzmann Machines Ruslan Salakutdinov and Geoffrey E. Hinton Amish Goel University of Illinois Urbana Champaign agoel10@illinois.edu December 2, 2016 Ruslan Salakutdinov and Geoffrey E. Hinton Amish

More information

Large-Scale Feature Learning with Spike-and-Slab Sparse Coding

Large-Scale Feature Learning with Spike-and-Slab Sparse Coding Large-Scale Feature Learning with Spike-and-Slab Sparse Coding Ian J. Goodfellow, Aaron Courville, Yoshua Bengio ICML 2012 Presented by Xin Yuan January 17, 2013 1 Outline Contributions Spike-and-Slab

More information

Learning Deep Architectures for AI. Part II - Vijay Chakilam

Learning Deep Architectures for AI. Part II - Vijay Chakilam Learning Deep Architectures for AI - Yoshua Bengio Part II - Vijay Chakilam Limitations of Perceptron x1 W, b 0,1 1,1 y x2 weight plane output =1 output =0 There is no value for W and b such that the model

More information

Introduction to Restricted Boltzmann Machines

Introduction to Restricted Boltzmann Machines Introduction to Restricted Boltzmann Machines Ilija Bogunovic and Edo Collins EPFL {ilija.bogunovic,edo.collins}@epfl.ch October 13, 2014 Introduction Ingredients: 1. Probabilistic graphical models (undirected,

More information

Chapter 16. Structured Probabilistic Models for Deep Learning

Chapter 16. Structured Probabilistic Models for Deep Learning Peng et al.: Deep Learning and Practice 1 Chapter 16 Structured Probabilistic Models for Deep Learning Peng et al.: Deep Learning and Practice 2 Structured Probabilistic Models way of using graphs to describe

More information

COMP9444 Neural Networks and Deep Learning 11. Boltzmann Machines. COMP9444 c Alan Blair, 2017

COMP9444 Neural Networks and Deep Learning 11. Boltzmann Machines. COMP9444 c Alan Blair, 2017 COMP9444 Neural Networks and Deep Learning 11. Boltzmann Machines COMP9444 17s2 Boltzmann Machines 1 Outline Content Addressable Memory Hopfield Network Generative Models Boltzmann Machine Restricted Boltzmann

More information

Learning Deep Architectures

Learning Deep Architectures Learning Deep Architectures Yoshua Bengio, U. Montreal Microsoft Cambridge, U.K. July 7th, 2009, Montreal Thanks to: Aaron Courville, Pascal Vincent, Dumitru Erhan, Olivier Delalleau, Olivier Breuleux,

More information

CSC321 Lecture 20: Autoencoders

CSC321 Lecture 20: Autoencoders CSC321 Lecture 20: Autoencoders Roger Grosse Roger Grosse CSC321 Lecture 20: Autoencoders 1 / 16 Overview Latent variable models so far: mixture models Boltzmann machines Both of these involve discrete

More information

An efficient way to learn deep generative models

An efficient way to learn deep generative models An efficient way to learn deep generative models Geoffrey Hinton Canadian Institute for Advanced Research & Department of Computer Science University of Toronto Joint work with: Ruslan Salakhutdinov, Yee-Whye

More information

Natural Language Understanding. Recap: probability, language models, and feedforward networks. Lecture 12: Recurrent Neural Networks and LSTMs

Natural Language Understanding. Recap: probability, language models, and feedforward networks. Lecture 12: Recurrent Neural Networks and LSTMs Natural Language Understanding Lecture 12: Recurrent Neural Networks and LSTMs Recap: probability, language models, and feedforward networks Simple Recurrent Networks Adam Lopez Credits: Mirella Lapata

More information

Restricted Boltzmann Machines

Restricted Boltzmann Machines Restricted Boltzmann Machines Boltzmann Machine(BM) A Boltzmann machine extends a stochastic Hopfield network to include hidden units. It has binary (0 or 1) visible vector unit x and hidden (latent) vector

More information

Deep Generative Models. (Unsupervised Learning)

Deep Generative Models. (Unsupervised Learning) Deep Generative Models (Unsupervised Learning) CEng 783 Deep Learning Fall 2017 Emre Akbaş Reminders Next week: project progress demos in class Describe your problem/goal What you have done so far What

More information

TUTORIAL PART 1 Unsupervised Learning

TUTORIAL PART 1 Unsupervised Learning TUTORIAL PART 1 Unsupervised Learning Marc'Aurelio Ranzato Department of Computer Science Univ. of Toronto ranzato@cs.toronto.edu Co-organizers: Honglak Lee, Yoshua Bengio, Geoff Hinton, Yann LeCun, Andrew

More information

Minimizing D(Q,P) def = Q(h)

Minimizing D(Q,P) def = Q(h) Inference Lecture 20: Variational Metods Kevin Murpy 29 November 2004 Inference means computing P( i v), were are te idden variables v are te visible variables. For discrete (eg binary) idden nodes, exact

More information

Deep Belief Networks are compact universal approximators

Deep Belief Networks are compact universal approximators 1 Deep Belief Networks are compact universal approximators Nicolas Le Roux 1, Yoshua Bengio 2 1 Microsoft Research Cambridge 2 University of Montreal Keywords: Deep Belief Networks, Universal Approximation

More information

How to do backpropagation in a brain. Geoffrey Hinton Canadian Institute for Advanced Research & University of Toronto

How to do backpropagation in a brain. Geoffrey Hinton Canadian Institute for Advanced Research & University of Toronto 1 How to do backpropagation in a brain Geoffrey Hinton Canadian Institute for Advanced Research & University of Toronto What is wrong with back-propagation? It requires labeled training data. (fixed) Almost

More information

Unsupervised Learning

Unsupervised Learning CS 3750 Advanced Machine Learning hkc6@pitt.edu Unsupervised Learning Data: Just data, no labels Goal: Learn some underlying hidden structure of the data P(, ) P( ) Principle Component Analysis (Dimensionality

More information

Chapter 20. Deep Generative Models

Chapter 20. Deep Generative Models Peng et al.: Deep Learning and Practice 1 Chapter 20 Deep Generative Models Peng et al.: Deep Learning and Practice 2 Generative Models Models that are able to Provide an estimate of the probability distribution

More information

arxiv: v2 [cs.ne] 22 Feb 2013

arxiv: v2 [cs.ne] 22 Feb 2013 Sparse Penalty in Deep Belief Networks: Using the Mixed Norm Constraint arxiv:1301.3533v2 [cs.ne] 22 Feb 2013 Xanadu C. Halkias DYNI, LSIS, Universitè du Sud, Avenue de l Université - BP20132, 83957 LA

More information

Jakub Hajic Artificial Intelligence Seminar I

Jakub Hajic Artificial Intelligence Seminar I Jakub Hajic Artificial Intelligence Seminar I. 11. 11. 2014 Outline Key concepts Deep Belief Networks Convolutional Neural Networks A couple of questions Convolution Perceptron Feedforward Neural Network

More information

Contrastive Divergence

Contrastive Divergence Contrastive Divergence Training Products of Experts by Minimizing CD Hinton, 2002 Helmut Puhr Institute for Theoretical Computer Science TU Graz June 9, 2010 Contents 1 Theory 2 Argument 3 Contrastive

More information

Deep Learning Autoencoder Models

Deep Learning Autoencoder Models Deep Learning Autoencoder Models Davide Bacciu Dipartimento di Informatica Università di Pisa Intelligent Systems for Pattern Recognition (ISPR) Generative Models Wrap-up Deep Learning Module Lecture Generative

More information

Restricted Boltzmann Machines

Restricted Boltzmann Machines Restricted Boltzmann Machines http://deeplearning4.org/rbm-mnist-tutorial.html Slides from Hugo Larochelle, Geoffrey Hinton, and Yoshua Bengio CSC321: Intro to Machine Learning and Neural Networks, Winter

More information

Denoising Autoencoders

Denoising Autoencoders Denoising Autoencoders Oliver Worm, Daniel Leinfelder 20.11.2013 Oliver Worm, Daniel Leinfelder Denoising Autoencoders 20.11.2013 1 / 11 Introduction Poor initialisation can lead to local minima 1986 -

More information

Course Structure. Psychology 452 Week 12: Deep Learning. Chapter 8 Discussion. Part I: Deep Learning: What and Why? Rufus. Rufus Processed By Fetch

Course Structure. Psychology 452 Week 12: Deep Learning. Chapter 8 Discussion. Part I: Deep Learning: What and Why? Rufus. Rufus Processed By Fetch Psychology 452 Week 12: Deep Learning What Is Deep Learning? Preliminary Ideas (that we already know!) The Restricted Boltzmann Machine (RBM) Many Layers of RBMs Pros and Cons of Deep Learning Course Structure

More information

Neural Networks. William Cohen [pilfered from: Ziv; Geoff Hinton; Yoshua Bengio; Yann LeCun; Hongkak Lee - NIPs 2010 tutorial ]

Neural Networks. William Cohen [pilfered from: Ziv; Geoff Hinton; Yoshua Bengio; Yann LeCun; Hongkak Lee - NIPs 2010 tutorial ] Neural Networks William Cohen 10-601 [pilfered from: Ziv; Geoff Hinton; Yoshua Bengio; Yann LeCun; Hongkak Lee - NIPs 2010 tutorial ] WHAT ARE NEURAL NETWORKS? William s notation Logis;c regression + 1

More information

Gaussian Cardinality Restricted Boltzmann Machines

Gaussian Cardinality Restricted Boltzmann Machines Proceedings of the Twenty-Ninth AAAI Conference on Artificial Intelligence Gaussian Cardinality Restricted Boltzmann Machines Cheng Wan, Xiaoming Jin, Guiguang Ding and Dou Shen School of Software, Tsinghua

More information

Representational Power of Restricted Boltzmann Machines and Deep Belief Networks. Nicolas Le Roux and Yoshua Bengio Presented by Colin Graber

Representational Power of Restricted Boltzmann Machines and Deep Belief Networks. Nicolas Le Roux and Yoshua Bengio Presented by Colin Graber Representational Power of Restricted Boltzmann Machines and Deep Belief Networks Nicolas Le Roux and Yoshua Bengio Presented by Colin Graber Introduction Representational abilities of functions with some

More information

Part 2. Representation Learning Algorithms

Part 2. Representation Learning Algorithms 53 Part 2 Representation Learning Algorithms 54 A neural network = running several logistic regressions at the same time If we feed a vector of inputs through a bunch of logis;c regression func;ons, then

More information

Speaker Representation and Verification Part II. by Vasileios Vasilakakis

Speaker Representation and Verification Part II. by Vasileios Vasilakakis Speaker Representation and Verification Part II by Vasileios Vasilakakis Outline -Approaches of Neural Networks in Speaker/Speech Recognition -Feed-Forward Neural Networks -Training with Back-propagation

More information

Basic Principles of Unsupervised and Unsupervised

Basic Principles of Unsupervised and Unsupervised Basic Principles of Unsupervised and Unsupervised Learning Toward Deep Learning Shun ichi Amari (RIKEN Brain Science Institute) collaborators: R. Karakida, M. Okada (U. Tokyo) Deep Learning Self Organization

More information

Deep Learning. What Is Deep Learning? The Rise of Deep Learning. Long History (in Hind Sight)

Deep Learning. What Is Deep Learning? The Rise of Deep Learning. Long History (in Hind Sight) CSCE 636 Neural Networks Instructor: Yoonsuck Choe Deep Learning What Is Deep Learning? Learning higher level abstractions/representations from data. Motivation: how the brain represents sensory information

More information

Deep Learning Basics Lecture 8: Autoencoder & DBM. Princeton University COS 495 Instructor: Yingyu Liang

Deep Learning Basics Lecture 8: Autoencoder & DBM. Princeton University COS 495 Instructor: Yingyu Liang Deep Learning Basics Lecture 8: Autoencoder & DBM Princeton University COS 495 Instructor: Yingyu Liang Autoencoder Autoencoder Neural networks trained to attempt to copy its input to its output Contain

More information

Probabilistic Graphical Models Homework 1: Due January 29, 2014 at 4 pm

Probabilistic Graphical Models Homework 1: Due January 29, 2014 at 4 pm Probabilistic Grapical Models 10-708 Homework 1: Due January 29, 2014 at 4 pm Directions. Tis omework assignment covers te material presented in Lectures 1-3. You must complete all four problems to obtain

More information

Modeling Documents with a Deep Boltzmann Machine

Modeling Documents with a Deep Boltzmann Machine Modeling Documents with a Deep Boltzmann Machine Nitish Srivastava, Ruslan Salakhutdinov & Geoffrey Hinton UAI 2013 Presented by Zhe Gan, Duke University November 14, 2014 1 / 15 Outline Replicated Softmax

More information

Learning Energy-Based Models of High-Dimensional Data

Learning Energy-Based Models of High-Dimensional Data Learning Energy-Based Models of High-Dimensional Data Geoffrey Hinton Max Welling Yee-Whye Teh Simon Osindero www.cs.toronto.edu/~hinton/energybasedmodelsweb.htm Discovering causal structure as a goal

More information

Au-delà de la Machine de Boltzmann Restreinte. Hugo Larochelle University of Toronto

Au-delà de la Machine de Boltzmann Restreinte. Hugo Larochelle University of Toronto Au-delà de la Machine de Boltzmann Restreinte Hugo Larochelle University of Toronto Introduction Restricted Boltzmann Machines (RBMs) are useful feature extractors They are mostly used to initialize deep

More information

Deep Belief Networks are Compact Universal Approximators

Deep Belief Networks are Compact Universal Approximators Deep Belief Networks are Compact Universal Approximators Franck Olivier Ndjakou Njeunje Applied Mathematics and Scientific Computation May 16, 2016 1 / 29 Outline 1 Introduction 2 Preliminaries Universal

More information

Overdispersed Variational Autoencoders

Overdispersed Variational Autoencoders Overdispersed Variational Autoencoders Harsil Sa, David Barber and Aleksandar Botev Department of Computer Science, University College London Alan Turing Institute arsil.sa.15@ucl.ac.uk, david.barber@ucl.ac.uk,

More information

Deep Learning. What Is Deep Learning? The Rise of Deep Learning. Long History (in Hind Sight)

Deep Learning. What Is Deep Learning? The Rise of Deep Learning. Long History (in Hind Sight) CSCE 636 Neural Networks Instructor: Yoonsuck Choe Deep Learning What Is Deep Learning? Learning higher level abstractions/representations from data. Motivation: how the brain represents sensory information

More information

THE hidden Markov model (HMM)-based parametric

THE hidden Markov model (HMM)-based parametric JOURNAL OF L A TEX CLASS FILES, VOL. 6, NO. 1, JANUARY 2007 1 Modeling Spectral Envelopes Using Restricted Boltzmann Macines and Deep Belief Networks for Statistical Parametric Speec Syntesis Zen-Hua Ling,

More information

Robust Classification using Boltzmann machines by Vasileios Vasilakakis

Robust Classification using Boltzmann machines by Vasileios Vasilakakis Robust Classification using Boltzmann machines by Vasileios Vasilakakis The scope of this report is to propose an architecture of Boltzmann machines that could be used in the context of classification,

More information

Deep Learning Architectures and Algorithms

Deep Learning Architectures and Algorithms Deep Learning Architectures and Algorithms In-Jung Kim 2016. 12. 2. Agenda Introduction to Deep Learning RBM and Auto-Encoders Convolutional Neural Networks Recurrent Neural Networks Reinforcement Learning

More information

An Efficient Learning Procedure for Deep Boltzmann Machines

An Efficient Learning Procedure for Deep Boltzmann Machines ARTICLE Communicated by Yoshua Bengio An Efficient Learning Procedure for Deep Boltzmann Machines Ruslan Salakhutdinov rsalakhu@utstat.toronto.edu Department of Statistics, University of Toronto, Toronto,

More information

Machine Learning and Data Mining. Multi-layer Perceptrons & Neural Networks: Basics. Prof. Alexander Ihler

Machine Learning and Data Mining. Multi-layer Perceptrons & Neural Networks: Basics. Prof. Alexander Ihler + Machine Learning and Data Mining Multi-layer Perceptrons & Neural Networks: Basics Prof. Alexander Ihler Linear Classifiers (Perceptrons) Linear Classifiers a linear classifier is a mapping which partitions

More information

Deep Neural Networks

Deep Neural Networks Deep Neural Networks DT2118 Speech and Speaker Recognition Giampiero Salvi KTH/CSC/TMH giampi@kth.se VT 2015 1 / 45 Outline State-to-Output Probability Model Artificial Neural Networks Perceptron Multi

More information

ARestricted Boltzmann machine (RBM) [1] is a probabilistic

ARestricted Boltzmann machine (RBM) [1] is a probabilistic 1 Matrix Product Operator Restricted Boltzmann Machines Cong Chen, Kim Batselier, Ching-Yun Ko, and Ngai Wong chencong@eee.hku.hk, k.batselier@tudelft.nl, cyko@eee.hku.hk, nwong@eee.hku.hk arxiv:1811.04608v1

More information

Bias-Variance Trade-Off in Hierarchical Probabilistic Models Using Higher-Order Feature Interactions

Bias-Variance Trade-Off in Hierarchical Probabilistic Models Using Higher-Order Feature Interactions - Trade-Off in Hierarchical Probabilistic Models Using Higher-Order Feature Interactions Simon Luo The University of Sydney Data61, CSIRO simon.luo@data61.csiro.au Mahito Sugiyama National Institute of

More information

ECE521 Lectures 9 Fully Connected Neural Networks

ECE521 Lectures 9 Fully Connected Neural Networks ECE521 Lectures 9 Fully Connected Neural Networks Outline Multi-class classification Learning multi-layer neural networks 2 Measuring distance in probability space We learnt that the squared L2 distance

More information

Using Deep Belief Nets to Learn Covariance Kernels for Gaussian Processes

Using Deep Belief Nets to Learn Covariance Kernels for Gaussian Processes Using Deep Belief Nets to Learn Covariance Kernels for Gaussian Processes Ruslan Salakhutdinov and Geoffrey Hinton Department of Computer Science, University of Toronto 6 King s College Rd, M5S 3G4, Canada

More information

STA 414/2104: Lecture 8

STA 414/2104: Lecture 8 STA 414/2104: Lecture 8 6-7 March 2017: Continuous Latent Variable Models, Neural networks With thanks to Russ Salakhutdinov, Jimmy Ba and others Outline Continuous latent variable models Background PCA

More information

CONVOLUTIONAL DEEP BELIEF NETWORKS

CONVOLUTIONAL DEEP BELIEF NETWORKS CONVOLUTIONAL DEEP BELIEF NETWORKS Talk by Emanuele Coviello Convolutional Deep Belief Networks for Scalable Unsupervised Learning of Hierarchical Representations Honglak Lee Roger Grosse Rajesh Ranganath

More information

Learning Deep Architectures

Learning Deep Architectures Learning Deep Architectures Yoshua Bengio, U. Montreal CIFAR NCAP Summer School 2009 August 6th, 2009, Montreal Main reference: Learning Deep Architectures for AI, Y. Bengio, to appear in Foundations and

More information

Measuring the Usefulness of Hidden Units in Boltzmann Machines with Mutual Information

Measuring the Usefulness of Hidden Units in Boltzmann Machines with Mutual Information Measuring the Usefulness of Hidden Units in Boltzmann Machines with Mutual Information Mathias Berglund, Tapani Raiko, and KyungHyun Cho Department of Information and Computer Science Aalto University

More information

A Hybrid Deep Learning Approach For Chaotic Time Series Prediction Based On Unsupervised Feature Learning

A Hybrid Deep Learning Approach For Chaotic Time Series Prediction Based On Unsupervised Feature Learning A Hybrid Deep Learning Approach For Chaotic Time Series Prediction Based On Unsupervised Feature Learning Norbert Ayine Agana Advisor: Abdollah Homaifar Autonomous Control & Information Technology Institute

More information

Restricted Boltzmann Machines for Collaborative Filtering

Restricted Boltzmann Machines for Collaborative Filtering Restricted Boltzmann Machines for Collaborative Filtering Authors: Ruslan Salakhutdinov Andriy Mnih Geoffrey Hinton Benjamin Schwehn Presentation by: Ioan Stanculescu 1 Overview The Netflix prize problem

More information

Neural networks. Chapter 20. Chapter 20 1

Neural networks. Chapter 20. Chapter 20 1 Neural networks Chapter 20 Chapter 20 1 Outline Brains Neural networks Perceptrons Multilayer networks Applications of neural networks Chapter 20 2 Brains 10 11 neurons of > 20 types, 10 14 synapses, 1ms

More information

Deep learning / Ian Goodfellow, Yoshua Bengio and Aaron Courville. - Cambridge, MA ; London, Spis treści

Deep learning / Ian Goodfellow, Yoshua Bengio and Aaron Courville. - Cambridge, MA ; London, Spis treści Deep learning / Ian Goodfellow, Yoshua Bengio and Aaron Courville. - Cambridge, MA ; London, 2017 Spis treści Website Acknowledgments Notation xiii xv xix 1 Introduction 1 1.1 Who Should Read This Book?

More information

CS 6501: Deep Learning for Computer Graphics. Basics of Neural Networks. Connelly Barnes

CS 6501: Deep Learning for Computer Graphics. Basics of Neural Networks. Connelly Barnes CS 6501: Deep Learning for Computer Graphics Basics of Neural Networks Connelly Barnes Overview Simple neural networks Perceptron Feedforward neural networks Multilayer perceptron and properties Autoencoders

More information

10. Artificial Neural Networks

10. Artificial Neural Networks Foundations of Machine Learning CentraleSupélec Fall 217 1. Artificial Neural Networks Chloé-Agathe Azencot Centre for Computational Biology, Mines ParisTech chloe-agathe.azencott@mines-paristech.fr Learning

More information

An Efficient Learning Procedure for Deep Boltzmann Machines Ruslan Salakhutdinov and Geoffrey Hinton

An Efficient Learning Procedure for Deep Boltzmann Machines Ruslan Salakhutdinov and Geoffrey Hinton Computer Science and Artificial Intelligence Laboratory Technical Report MIT-CSAIL-TR-2010-037 August 4, 2010 An Efficient Learning Procedure for Deep Boltzmann Machines Ruslan Salakhutdinov and Geoffrey

More information

Need for Deep Networks Perceptron. Can only model linear functions. Kernel Machines. Non-linearity provided by kernels

Need for Deep Networks Perceptron. Can only model linear functions. Kernel Machines. Non-linearity provided by kernels Need for Deep Networks Perceptron Can only model linear functions Kernel Machines Non-linearity provided by kernels Need to design appropriate kernels (possibly selecting from a set, i.e. kernel learning)

More information

Machine Learning. Neural Networks

Machine Learning. Neural Networks Machine Learning Neural Networks Bryan Pardo, Northwestern University, Machine Learning EECS 349 Fall 2007 Biological Analogy Bryan Pardo, Northwestern University, Machine Learning EECS 349 Fall 2007 THE

More information

CENG 783. Special topics in. Deep Learning. AlchemyAPI. Week 14. Sinan Kalkan

CENG 783. Special topics in. Deep Learning. AlchemyAPI. Week 14. Sinan Kalkan CENG 783 Special topics in Deep Learning AlchemyAPI Week 14 Sinan Kalkan Today Hopfield Networks Boltzmann Machines Deep BM, Restricted BM Generative Adversarial Networks Variational Auto-encoders Autoregressive

More information

Deep Learning & Neural Networks Lecture 2

Deep Learning & Neural Networks Lecture 2 Deep Learning & Neural Networks Lecture 2 Kevin Duh Graduate School of Information Science Nara Institute of Science and Technology Jan 16, 2014 2/45 Today s Topics 1 General Ideas in Deep Learning Motivation

More information

Opportunities and challenges in quantum-enhanced machine learning in near-term quantum computers

Opportunities and challenges in quantum-enhanced machine learning in near-term quantum computers Opportunities and challenges in quantum-enhanced machine learning in near-term quantum computers Alejandro Perdomo-Ortiz Senior Research Scientist, Quantum AI Lab. at NASA Ames Research Center and at the

More information

Implementation of a Restricted Boltzmann Machine in a Spiking Neural Network

Implementation of a Restricted Boltzmann Machine in a Spiking Neural Network Implementation of a Restricted Boltzmann Machine in a Spiking Neural Network Srinjoy Das Department of Electrical and Computer Engineering University of California, San Diego srinjoyd@gmail.com Bruno Umbria

More information

Undirected Graphical Models: Markov Random Fields

Undirected Graphical Models: Markov Random Fields Undirected Graphical Models: Markov Random Fields 40-956 Advanced Topics in AI: Probabilistic Graphical Models Sharif University of Technology Soleymani Spring 2015 Markov Random Field Structure: undirected

More information

Learning Tetris. 1 Tetris. February 3, 2009

Learning Tetris. 1 Tetris. February 3, 2009 Learning Tetris Matt Zucker Andrew Maas February 3, 2009 1 Tetris The Tetris game has been used as a benchmark for Machine Learning tasks because its large state space (over 2 200 cell configurations are

More information

Deep Generative Models

Deep Generative Models Deep Generative Models Durk Kingma Max Welling Deep Probabilistic Models Worksop Wednesday, 1st of Oct, 2014 D.P. Kingma Deep generative models Transformations between Bayes nets and Neural nets Transformation

More information

Notes on Neural Networks

Notes on Neural Networks Artificial neurons otes on eural etwors Paulo Eduardo Rauber 205 Consider te data set D {(x i y i ) i { n} x i R m y i R d } Te tas of supervised learning consists on finding a function f : R m R d tat

More information

Energy Based Models. Stefano Ermon, Aditya Grover. Stanford University. Lecture 13

Energy Based Models. Stefano Ermon, Aditya Grover. Stanford University. Lecture 13 Energy Based Models Stefano Ermon, Aditya Grover Stanford University Lecture 13 Stefano Ermon, Aditya Grover (AI Lab) Deep Generative Models Lecture 13 1 / 21 Summary Story so far Representation: Latent

More information

Stochastic Gradient Estimate Variance in Contrastive Divergence and Persistent Contrastive Divergence

Stochastic Gradient Estimate Variance in Contrastive Divergence and Persistent Contrastive Divergence ESANN 0 proceedings, European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning. Bruges (Belgium), 7-9 April 0, idoc.com publ., ISBN 97-7707-. Stochastic Gradient

More information

Density estimation. Computing, and avoiding, partition functions. Iain Murray

Density estimation. Computing, and avoiding, partition functions. Iain Murray Density estimation Computing, and avoiding, partition functions Roadmap: Motivation: density estimation Understanding annealing/tempering NADE Iain Murray School of Informatics, University of Edinburgh

More information

Training an RBM: Contrastive Divergence. Sargur N. Srihari

Training an RBM: Contrastive Divergence. Sargur N. Srihari Training an RBM: Contrastive Divergence Sargur N. srihari@cedar.buffalo.edu Topics in Partition Function Definition of Partition Function 1. The log-likelihood gradient 2. Stochastic axiu likelihood and

More information

Logistic Regression & Neural Networks

Logistic Regression & Neural Networks Logistic Regression & Neural Networks CMSC 723 / LING 723 / INST 725 Marine Carpuat Slides credit: Graham Neubig, Jacob Eisenstein Logistic Regression Perceptron & Probabilities What if we want a probability

More information

Need for Deep Networks Perceptron. Can only model linear functions. Kernel Machines. Non-linearity provided by kernels

Need for Deep Networks Perceptron. Can only model linear functions. Kernel Machines. Non-linearity provided by kernels Need for Deep Networks Perceptron Can only model linear functions Kernel Machines Non-linearity provided by kernels Need to design appropriate kernels (possibly selecting from a set, i.e. kernel learning)

More information

STA 414/2104: Lecture 8

STA 414/2104: Lecture 8 STA 414/2104: Lecture 8 6-7 March 2017: Continuous Latent Variable Models, Neural networks Delivered by Mark Ebden With thanks to Russ Salakhutdinov, Jimmy Ba and others Outline Continuous latent variable

More information

Inductive Principles for Restricted Boltzmann Machine Learning

Inductive Principles for Restricted Boltzmann Machine Learning Inductive Principles for Restricted Boltzmann Machine Learning Benjamin Marlin Department of Computer Science University of British Columbia Joint work with Kevin Swersky, Bo Chen and Nando de Freitas

More information

Algorithms other than SGD. CS6787 Lecture 10 Fall 2017

Algorithms other than SGD. CS6787 Lecture 10 Fall 2017 Algorithms other than SGD CS6787 Lecture 10 Fall 2017 Machine learning is not just SGD Once a model is trained, we need to use it to classify new examples This inference task is not computed with SGD There

More information

Introduction to Machine Learning. Recitation 8. w 2, b 2. w 1, b 1. z 0 z 1. The function we want to minimize is the loss over all examples: f =

Introduction to Machine Learning. Recitation 8. w 2, b 2. w 1, b 1. z 0 z 1. The function we want to minimize is the loss over all examples: f = Introduction to Macine Learning Lecturer: Regev Scweiger Recitation 8 Fall Semester Scribe: Regev Scweiger 8.1 Backpropagation We will develop and review te backpropagation algoritm for neural networks.

More information

Chapter 11. Stochastic Methods Rooted in Statistical Mechanics

Chapter 11. Stochastic Methods Rooted in Statistical Mechanics Chapter 11. Stochastic Methods Rooted in Statistical Mechanics Neural Networks and Learning Machines (Haykin) Lecture Notes on Self-learning Neural Algorithms Byoung-Tak Zhang School of Computer Science

More information

Introduction to Convolutional Neural Networks (CNNs)

Introduction to Convolutional Neural Networks (CNNs) Introduction to Convolutional Neural Networks (CNNs) nojunk@snu.ac.kr http://mipal.snu.ac.kr Department of Transdisciplinary Studies Seoul National University, Korea Jan. 2016 Many slides are from Fei-Fei

More information

Artificial Intelligence

Artificial Intelligence Artificial Intelligence Jeff Clune Assistant Professor Evolving Artificial Intelligence Laboratory Announcements Be making progress on your projects! Three Types of Learning Unsupervised Supervised Reinforcement

More information

Autoencoders and Score Matching. Based Models. Kevin Swersky Marc Aurelio Ranzato David Buchman Benjamin M. Marlin Nando de Freitas

Autoencoders and Score Matching. Based Models. Kevin Swersky Marc Aurelio Ranzato David Buchman Benjamin M. Marlin Nando de Freitas On for Energy Based Models Kevin Swersky Marc Aurelio Ranzato David Buchman Benjamin M. Marlin Nando de Freitas Toronto Machine Learning Group Meeting, 2011 Motivation Models Learning Goal: Unsupervised

More information

Notes on Boltzmann Machines

Notes on Boltzmann Machines 1 Notes on Boltzmann Machines Patrick Kenny Centre de recherche informatique de Montréal Patrick.Kenny@crim.ca I. INTRODUCTION Boltzmann machines are probability distributions on high dimensional binary

More information

Deep Learning Basics Lecture 7: Factor Analysis. Princeton University COS 495 Instructor: Yingyu Liang

Deep Learning Basics Lecture 7: Factor Analysis. Princeton University COS 495 Instructor: Yingyu Liang Deep Learning Basics Lecture 7: Factor Analysis Princeton University COS 495 Instructor: Yingyu Liang Supervised v.s. Unsupervised Math formulation for supervised learning Given training data x i, y i

More information

Hopfield Networks and Boltzmann Machines. Christian Borgelt Artificial Neural Networks and Deep Learning 296

Hopfield Networks and Boltzmann Machines. Christian Borgelt Artificial Neural Networks and Deep Learning 296 Hopfield Networks and Boltzmann Machines Christian Borgelt Artificial Neural Networks and Deep Learning 296 Hopfield Networks A Hopfield network is a neural network with a graph G = (U,C) that satisfies

More information

Variational Inference via Stochastic Backpropagation

Variational Inference via Stochastic Backpropagation Variational Inference via Stochastic Backpropagation Kai Fan February 27, 2016 Preliminaries Stochastic Backpropagation Variational Auto-Encoding Related Work Summary Outline Preliminaries Stochastic Backpropagation

More information