What and where: A Bayesian inference theory of attention
|
|
- Shana Osborne
- 5 years ago
- Views:
Transcription
1 What and where: A Bayesian inference theory of attention Sharat Chikkerur, Thomas Serre, Cheston Tan & Tomaso Poggio CBCL, McGovern Institute for Brain Research, MIT
2 Preliminaries Outline Perception & Bayesian inference Background & motivation Theory Attention as inference Bayesian model Computational model Model properties Applications on real-world images Predicting human eye movements Improving object recognition
3 Perception as Bayesian inference Mumford and Lee, Hierarchical Bayesian Inference in the Visual Cortex, JOSA, 20(7), 2003 x IT Recurrent feed-forward/feedback loops integrate bottom up information with top down priors Bottom-up signals : Data dependent Top-down signals : Task dependent Top down signals provide context information and help to disambiguate bottom-up signals x V4 x V2 x V1 x 0
4 Bottom up vs. top-down Hegde J. and Felleman J., Reappraising the functional implications of the primate visual anatomical hierarchy, Neuroscientist, 13(5), 2007
5 Bottom up vs. top-down
6 Mathematical framework
7 Bayesian generative models X System () f ( data ) Y ( state ) X ( data ) Y Statistical learning view: Generative model view: Y = f(x), X-data, Y-class Y X-random, Y-random X~P(X Y), ( Y X )! P( X Y) P( Y) P Y X X
8 x IT x V Perception: bottom-up & topdown Recall, P( A,B) = P( A B) P( B) = P( B A) P( A) P( A B) P( B) P( B A) = P( A) P( A) = P( A,B)! For the given network, B ( x,x,x ) = P( x x ) P( x x ) P( x ) P P IT V 0 0 ( xv,x0 xit ) = P( x0 xv,xit ) P( xv xit ) = P( x x ) P( x x ) 0 V V V V IT IT IT x 0 Inference: P P ( ) ( x0 xv,xit ) P( xv xit ) xv x0,xit = P( x0 xit ) P( x x ) P( x x ) 0 V V IT Bottom-up Top-down
9 Belief propagation ( + π(e Prior e + ( + π(x)=p(x e e+ ( + )P(x e π(e + ( + π(y)=p(y e X Y ( π(x b(x)α λ(x) λ y ( x (x)=p(e - Y ( λ(y)p(y x ( y λ(y)=p(e - e - ( - λ(e Evidence
10 Biological plausibility George D. and Hawkins J., A hierarchical Bayesian model of invariant pattern recognition in the visual cortex, IJCNN, 2005
11 U X Y 1 Y 2 Y 3 ( ) ( ) ( ) ( ) x ë x ë x = ë x ë y y 1 y 3 2 ( ) ( ) ( )! x u x P x ë = u ë ( ) ( ) ( )! u u D u x P = x D ( ) ( ) ( ) ( ) ( ) x y P x ë x ë x D = c y D y y x ! Trees
12 U 1 X Y 1 Y 2 Y 3 ( ) ( ) ( ) ( )! x ë x ë x ë = x ë y y y ( ) ( ) ( ) ( )!! x, u u D u u x P x ë = u ë ( ) ( ) ( ) ( )! u u D u D u u x P = x D u ( ) ( ) ( ) ( ) ( ) x y P x ë x ë x D = c y D y y x ! U 2 Polytrees
13 Attention Background & motivation
14 Visual processing: what and Ventral stream Dorsal stream where Ventral ( what ) stream: Processes shape information Responsible for object recognition Progressive loss of location information Dorsal ( where ) stream: Processes location and motion information Progressive loss of form information Form and location is processed concurrently and (almost) independently of each other How does the brain combine form and location information?
15 Ventral stream: invariant recognition Psychophysics V4 IT Reynolds, Chelazzi & Desimone 99 Serre Oliva Poggio 2007 Zoccolan Kouh Poggio DiCarlo 2007 How does the brain recognize objects under clutter? Figures from Serre et al, Hung et al.
16 Parallel vs. serial processing Attention is needed to recognize objects under clutter
17 Filter theory (Broadbent) Biased competition (Desimone) Feature integration theory (Treisman) Guided search (Wolfe) Scanpath theory (Noton) Bayesian surprise (Itti) Bottleneck (Tsotsos) Computational Role Biology V1 V4 MT LIP FEF Attention Everybody knows what Contrast attention gain is -William James, 1907 Response gain Modulation under spatial attention Modulation under feature attention Pop-out Serial vs. Parallel Bottom-up vs. Top-down Effects
18 Bridging the gap Conceptual models (theories) Provide justifications not implementations Computational models Model behavior (eye-movements) Cannot model physiological effects Phenomenological models Model specific physiological effects Cannot provide theory Bridging the gap Phenomenological, predicts behavior, theory
19 A theoretical framework
20 Bayesian model Kersten & Yuille 04 Assumption: visual system selects and localizes objects, one at a time
21 Bayesian model Assumption: object location and identity are marginally independent of each other
22 Bayesian model Assumption: Every object is generated using a set of N complex features each of which may be present or absent
23 Bayesian model F i : Location/scale invariant features
24 Computational model
25 Relation to biology PFC LIP/FEF IT V4 V2 Feature-based Spatial attention: attention: What is Where at location is object L? O?
26 Model description Where What L F i x i Feature-maps N Feature-maps Image
27 Model properties: invariance Where What L F i x i N
28 Model properties: crowding Where What L F i x i N
29 Model: spatial attention L F i X F i l N * * * What is at location X?
30 Model: feature-based attention X L F i F i l * * * N Where is object X?
31 Model properties
32 Spatial Invariance
33 Spatial Attention
34 Feature Attention
35 Feature Popout
36 Parallel vs. Serial Search
37 Application I: Predicting eye-movements
38 Predicting eye movements Eye movements can be considered as a proxy for attention Cues influencing eye-movements Bottom-up image saliency Top-down feature biases Top-down spatial bias Evaluation
39 Model can predict human eye-movements Top-down Bottom-up spatialattention and feature attention Method Method ROC area (Cars) ROC area (Pedestrian) ROC area (absolute) Bruce and Tsotos 06 Itti et al % Torralba et al. Itti et al % Proposed Proposed 80.4% Humans 87.8% 72.8% 42.3% 72.7% 77.1% 77.9% 80.1% 87.4%
40 Application II: Improving recognition
41 Effect of clutter on detection recognition without attention recognition under attention
42 Recognition performance improves with attention Chikkerur, Serre, Tan & Poggio (in submission, Vision Research)
43 Recognition performance improves with attention Chikkerur, Serre, Tan & Poggio (in prep)
44 Theory Summary Attention is part of the inference process that solves the problem of what is where. Computational model We describe a computational model and relate it to functional anatomy of attention. Attentional phenomena (pop-out, multiplicative modulation, contrast response) are predicted by the model. Applications Predicting human eye movements. Improving object recognition
45 Thank you!
46
47 Relation to prior work
48 Feedback and its role Reconstruction Mental Imagery Murray J. F., Visual recognition, inference and coding using learned sparse overcomplete representations, PhD thesis, UCSD, 2005 Hinton G. E, Osindero S. and Teh. Y, A fast learning algorithm for deep belief nets, Neural computation, vol. 18, 2006
49 Feedback and its role Visual attention/segmentation Murray J. F., Visual recognition, inference and coding using learned sparse overcomplete representations, PhD thesis, UCSD, 2005 Fukushima K., A neural network model for selective attention in visual pattern recognition, Biological Cybernetics, vol. 55, 1986
50 Predicting physiological effects
51 Spatial attention McAdams and Maunsell 99 Model Unattended Attended
52 Feature-based attention Bichot and Desimone 05 Model
53 Contrast gain vs. Response gain Trujillo and Treue 02 Mc Adams and Maunsell 99
54 Attentional effects in MT: popout
55 MT: Feature based attention
56 MT: Multi-modal interaction
Deep learning in the visual cortex
Deep learning in the visual cortex Thomas Serre Brown University. Fundamentals of primate vision. Computational mechanisms of rapid recognition and feedforward processing. Beyond feedforward processing:
More informationClass Learning Data Representations: beyond DeepLearning: the Magic Theory. Tomaso Poggio. Thursday, December 5, 13
Class 24-26 Learning Data Representations: beyond DeepLearning: the Magic Theory Tomaso Poggio Connection with the topic of learning theory 2 Notices of the American Mathematical Society (AMS), Vol. 50,
More informationA Biologically-Inspired Model for Recognition of Overlapped Patterns
A Biologically-Inspired Model for Recognition of Overlapped Patterns Mohammad Saifullah Department of Computer and Information Science Linkoping University, Sweden Mohammad.saifullah@liu.se Abstract. In
More informationHow to make computers work like the brain
How to make computers work like the brain (without really solving the brain) Dileep George a single special machine can be made to do the work of all. It could in fact be made to work as a model of any
More informationNeural Networks. Henrik I. Christensen. Computer Science and Engineering University of California, San Diego
Neural Networks Henrik I. Christensen Computer Science and Engineering University of California, San Diego http://www.hichristensen.net Henrik I. Christensen (UCSD) Neural Networks 1 / 39 Introduction
More informationCompetitive Learning for Deep Temporal Networks
Competitive Learning for Deep Temporal Networks Robert Gens Computer Science and Engineering University of Washington Seattle, WA 98195 rcg@cs.washington.edu Pedro Domingos Computer Science and Engineering
More informationHierarchy. Will Penny. 24th March Hierarchy. Will Penny. Linear Models. Convergence. Nonlinear Models. References
24th March 2011 Update Hierarchical Model Rao and Ballard (1999) presented a hierarchical model of visual cortex to show how classical and extra-classical Receptive Field (RF) effects could be explained
More informationÂngelo Cardoso 27 May, Symbolic and Sub-Symbolic Learning Course Instituto Superior Técnico
BIOLOGICALLY INSPIRED COMPUTER MODELS FOR VISUAL RECOGNITION Ângelo Cardoso 27 May, 2010 Symbolic and Sub-Symbolic Learning Course Instituto Superior Técnico Index Human Vision Retinal Ganglion Cells Simple
More informationRepresentation Learning in Sensory Cortex: a theory
CBMM Memo No. 026 November 14, 2014 Representation Learning in Sensory Cortex: a theory by Fabio Anselmi, and Tomaso Armando Poggio, Center for Brains, Minds and Machines, McGovern Institute, Massachusetts
More informationFundamentals of Computational Neuroscience 2e
Fundamentals of Computational Neuroscience 2e January 1, 2010 Chapter 10: The cognitive brain Hierarchical maps and attentive vision A. Ventral visual pathway B. Layered cortical maps Receptive field size
More informationTUTORIAL 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 informationCharles Cadieu, Minjoon Kouh, Anitha Pasupathy, Charles E. Connor, Maximilian Riesenhuber and Tomaso Poggio
Charles Cadieu, Minjoon Kouh, Anitha Pasupathy, Charles E. Connor, Maximilian Riesenhuber and Tomaso Poggio J Neurophysiol 98:733-75, 27. First published Jun 27, 27; doi:.52/jn.265.26 You might find this
More informationOn The Equivalence of Hierarchical Temporal Memory and Neural Nets
On The Equivalence of Hierarchical Temporal Memory and Neural Nets Bedeho Mesghina Wolde Mender December 7, 2009 Abstract In this paper we present a rigorous definition of classification in a common family
More informationThe 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 informationAchievable rates for pattern recognition
Achievable rates for pattern recognition M Brandon Westover Joseph A O Sullivan Washington University in Saint Louis Departments of Physics and Electrical Engineering Goals of Information Theory Models
More informationLearning and Memory in Neural Networks
Learning and Memory in Neural Networks Guy Billings, Neuroinformatics Doctoral Training Centre, The School of Informatics, The University of Edinburgh, UK. Neural networks consist of computational units
More informationKnowledge 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 informationVisual Recognition and Inference Using Dynamic Overcomplete Sparse Learning
LETTER Communicated by Rajesh Rao Visual Recognition and Inference Using Dynamic Overcomplete Sparse Learning Joseph F. Murray murrayjf@mit.edu Massachusetts Institute of Technology, Brain and Cognitive
More informationIntroduction Biologically Motivated Crude Model Backpropagation
Introduction Biologically Motivated Crude Model Backpropagation 1 McCulloch-Pitts Neurons In 1943 Warren S. McCulloch, a neuroscientist, and Walter Pitts, a logician, published A logical calculus of the
More informationRegML 2018 Class 8 Deep learning
RegML 2018 Class 8 Deep learning Lorenzo Rosasco UNIGE-MIT-IIT June 18, 2018 Supervised vs unsupervised learning? So far we have been thinking of learning schemes made in two steps f(x) = w, Φ(x) F, x
More informationGeneralization and Properties of the Neural Response Jake Bouvrie, Tomaso Poggio, Lorenzo Rosasco, Steve Smale, and Andre Wibisono
Computer Science and Artificial Intelligence Laboratory Technical Report MIT-CSAIL-TR-2010-051 CBCL-292 November 19, 2010 Generalization and Properties of the Neural Response Jake Bouvrie, Tomaso Poggio,
More informationREVISIT ENCODER & DECODER
PERCEPTION-LINK BEHAVIOR MODEL: REVISIT ENCODER & DECODER IMI PHD Presentation Presenter: William Gu Yuanlong (PhD student) Supervisor: Assoc. Prof. Gerald Seet Gim Lee Co-Supervisor: Prof. Nadia Magnenat-Thalmann
More informationIs the Human Visual System Invariant to Translation and Scale?
The AAAI 207 Spring Symposium on Science of Intelligence: Computational Principles of Natural and Artificial Intelligence Technical Report SS-7-07 Is the Human Visual System Invariant to Translation and
More informationComputer Science and Artificial Intelligence Laboratory Technical Report
Computer Science and Artificial Intelligence Laboratory Technical Report MIT-CSAIL-TR-2013-019 CBCL-313 August 6, 2013 Does invariant recognition predict tuning of neurons in sensory cortex? Tomaso Poggio,
More informationThe functional organization of the visual cortex in primates
The functional organization of the visual cortex in primates Dominated by LGN M-cell input Drosal stream for motion perception & spatial localization V5 LIP/7a V2 V4 IT Ventral stream for object recognition
More informationDeep 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 informationSUPPLEMENTARY INFORMATION
Supplementary discussion 1: Most excitatory and suppressive stimuli for model neurons The model allows us to determine, for each model neuron, the set of most excitatory and suppresive features. First,
More informationRealistic Modeling of Simple and Complex Cell Tuning in the HMAX Model, and Implications for Invariant Object Recognition in Cortex
massachusetts institute of technology computer science and artificial intelligence laboratory Realistic Modeling of Simple and Complex Cell Tuning in the HMAX Model, and Implications for Invariant Object
More informationTHE COMPUTATIONAL MAGIC OF THE VENTRAL STREAM
December 6, 2011 THE COMPUTATIONAL MAGIC OF THE VENTRAL STREAM Online archived report: usage instructions. This is version 2 of a report first published online on July 20, 2011 (npre.2011.6117.1) and it
More informationExpectation Propagation in Factor Graphs: A Tutorial
DRAFT: Version 0.1, 28 October 2005. Do not distribute. Expectation Propagation in Factor Graphs: A Tutorial Charles Sutton October 28, 2005 Abstract Expectation propagation is an important variational
More informationExperimental design of fmri studies
Methods & Models for fmri Analysis 2017 Experimental design of fmri studies Sara Tomiello With many thanks for slides & images to: Sandra Iglesias, Klaas Enno Stephan, FIL Methods group, Christian Ruff
More informationExperimental design of fmri studies
Experimental design of fmri studies Sandra Iglesias With many thanks for slides & images to: Klaas Enno Stephan, FIL Methods group, Christian Ruff SPM Course 2015 Overview of SPM Image time-series Kernel
More informationDeep 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 informationI-theory on depth vs width: hierarchical function composition
CBMM Memo No. 041 December 29, 2015 I-theory on depth vs width: hierarchical function composition by Tomaso Poggio with Fabio Anselmi and Lorenzo Rosasco Abstract Deep learning networks with convolution,
More informationModeling retinal high and low contrast sensitivity lters. T. Lourens. Abstract
Modeling retinal high and low contrast sensitivity lters T. Lourens Department of Computer Science University of Groningen P.O. Box 800, 9700 AV Groningen, The Netherlands E-mail: tino@cs.rug.nl Abstract
More informationArtificial 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 informationUnderstanding Aha! Moments
Understanding Aha! Moments Hermish Mehta Department of Electrical Engineering & Computer Sciences University of California, Berkeley Berkeley, CA 94720 hermish@berkeley.edu Abstract In this paper, we explore
More informationPILCO: A Model-Based and Data-Efficient Approach to Policy Search
PILCO: A Model-Based and Data-Efficient Approach to Policy Search (M.P. Deisenroth and C.E. Rasmussen) CSC2541 November 4, 2016 PILCO Graphical Model PILCO Probabilistic Inference for Learning COntrol
More informationUnsupervised Discovery of Nonlinear Structure Using Contrastive Backpropagation
Cognitive Science 30 (2006) 725 731 Copyright 2006 Cognitive Science Society, Inc. All rights reserved. Unsupervised Discovery of Nonlinear Structure Using Contrastive Backpropagation Geoffrey Hinton,
More informationIntroduction to Deep Learning
Introduction to Deep Learning Some slides and images are taken from: David Wolfe Corne Wikipedia Geoffrey A. Hinton https://www.macs.hw.ac.uk/~dwcorne/teaching/introdl.ppt Feedforward networks for function
More informationUNSUPERVISED 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 informationFlexible Gating of Contextual Influences in Natural Vision. Odelia Schwartz University of Miami Oct 2015
Flexible Gating of Contextual Influences in Natural Vision Odelia Schwartz University of Miami Oct 05 Contextual influences Perceptual illusions: no man is an island.. Review paper on context: Schwartz,
More informationCOURSE INTRODUCTION. J. Elder CSE 6390/PSYC 6225 Computational Modeling of Visual Perception
COURSE INTRODUCTION COMPUTATIONAL MODELING OF VISUAL PERCEPTION 2 The goal of this course is to provide a framework and computational tools for modeling visual inference, motivated by interesting examples
More informationLecture 8: Introduction to Deep Learning: Part 2 (More on backpropagation, and ConvNets)
COS 402 Machine Learning and Artificial Intelligence Fall 2016 Lecture 8: Introduction to Deep Learning: Part 2 (More on backpropagation, and ConvNets) Sanjeev Arora Elad Hazan Recap: Structure of a deep
More informationBayesian Computation in Recurrent Neural Circuits
Bayesian Computation in Recurrent Neural Circuits Rajesh P. N. Rao Department of Computer Science and Engineering University of Washington Seattle, WA 98195 E-mail: rao@cs.washington.edu Appeared in: Neural
More informationExperimental design of fmri studies
Experimental design of fmri studies Zurich SPM Course 2016 Sandra Iglesias Translational Neuromodeling Unit (TNU) Institute for Biomedical Engineering (IBT) University and ETH Zürich With many thanks for
More informationClicker Question. Discussion Question
Connectomics Networks and Graph Theory A network is a set of nodes connected by edges The field of graph theory has developed a number of measures to analyze networks Mean shortest path length: the average
More informationStatistical Learning Reading Assignments
Statistical Learning Reading Assignments S. Gong et al. Dynamic Vision: From Images to Face Recognition, Imperial College Press, 2001 (Chapt. 3, hard copy). T. Evgeniou, M. Pontil, and T. Poggio, "Statistical
More informationSustained and transient channels
Sustained and transient channels Chapter 5, pp. 141 164 19.12.2006 Some models of masking are based on two channels with different temporal properties Dual-channel models Evidence for two different channels
More informationPredicting response time and error rates in visual search
Predicting response time and error rates in visual search Bo Chen Caltech bchen3@caltech.edu Vidhya Navalpakkam Yahoo! Research nvidhya@yahoo-inc.com Pietro Perona Caltech perona@caltech.edu Abstract A
More informationExperimental design of fmri studies & Resting-State fmri
Methods & Models for fmri Analysis 2016 Experimental design of fmri studies & Resting-State fmri Sandra Iglesias With many thanks for slides & images to: Klaas Enno Stephan, FIL Methods group, Christian
More informationProbabilistic Models in Theoretical Neuroscience
Probabilistic Models in Theoretical Neuroscience visible unit Boltzmann machine semi-restricted Boltzmann machine restricted Boltzmann machine hidden unit Neural models of probabilistic sampling: introduction
More informationarxiv: v3 [cs.lg] 18 Mar 2013
Hierarchical Data Representation Model - Multi-layer NMF arxiv:1301.6316v3 [cs.lg] 18 Mar 2013 Hyun Ah Song Department of Electrical Engineering KAIST Daejeon, 305-701 hyunahsong@kaist.ac.kr Abstract Soo-Young
More informationLearning 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 informationDeep 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 informationDerived Distance: Beyond a model, towards a theory
Derived Distance: Beyond a model, towards a theory 9.520 April 23 2008 Jake Bouvrie work with Steve Smale, Tomaso Poggio, Andrea Caponnetto and Lorenzo Rosasco Reference: Smale, S., T. Poggio, A. Caponnetto,
More informationHierarchical Sparse Bayesian Learning. Pierre Garrigues UC Berkeley
Hierarchical Sparse Bayesian Learning Pierre Garrigues UC Berkeley Outline Motivation Description of the model Inference Learning Results Motivation Assumption: sensory systems are adapted to the statistical
More informationArtificial Neural Networks. Historical description
Artificial Neural Networks Historical description Victor G. Lopez 1 / 23 Artificial Neural Networks (ANN) An artificial neural network is a computational model that attempts to emulate the functions of
More informationA General Mechanism for Tuning: Gain Control Circuits and Synapses Underlie Tuning of Cortical Neurons
massachusetts institute of technology computer science and artificial intelligence laboratory A General Mechanism for Tuning: Gain Control Circuits and Synapses Underlie Tuning of Cortical Neurons Minjoon
More informationVentral Visual Stream and Deep Networks
Ma191b Winter 2017 Geometry of Neuroscience References for this lecture: Tomaso A. Poggio and Fabio Anselmi, Visual Cortex and Deep Networks, MIT Press, 2016 F. Cucker, S. Smale, On the mathematical foundations
More informationDistinguish between different types of scenes. Matching human perception Understanding the environment
Scene Recognition Adriana Kovashka UTCS, PhD student Problem Statement Distinguish between different types of scenes Applications Matching human perception Understanding the environment Indexing of images
More informationUnsupervised Learning of Hierarchical Models. in collaboration with Josh Susskind and Vlad Mnih
Unsupervised Learning of Hierarchical Models Marc'Aurelio Ranzato Geoff Hinton in collaboration with Josh Susskind and Vlad Mnih Advanced Machine Learning, 9 March 2011 Example: facial expression recognition
More informationThe connection of dropout and Bayesian statistics
The connection of dropout and Bayesian statistics Interpretation of dropout as approximate Bayesian modelling of NN http://mlg.eng.cam.ac.uk/yarin/thesis/thesis.pdf Dropout Geoffrey Hinton Google, University
More informationConfidence Estimation Methods for Neural Networks: A Practical Comparison
, 6-8 000, Confidence Estimation Methods for : A Practical Comparison G. Papadopoulos, P.J. Edwards, A.F. Murray Department of Electronics and Electrical Engineering, University of Edinburgh Abstract.
More informationBayesian Networks: Construction, Inference, Learning and Causal Interpretation. Volker Tresp Summer 2016
Bayesian Networks: Construction, Inference, Learning and Causal Interpretation Volker Tresp Summer 2016 1 Introduction So far we were mostly concerned with supervised learning: we predicted one or several
More informationDeep Learning of Invariant Spatiotemporal Features from Video. Bo Chen, Jo-Anne Ting, Ben Marlin, Nando de Freitas University of British Columbia
Deep Learning of Invariant Spatiotemporal Features from Video Bo Chen, Jo-Anne Ting, Ben Marlin, Nando de Freitas University of British Columbia Introduction Focus: Unsupervised feature extraction from
More informationProbabilistic Graphical Models for Image Analysis - Lecture 1
Probabilistic Graphical Models for Image Analysis - Lecture 1 Alexey Gronskiy, Stefan Bauer 21 September 2018 Max Planck ETH Center for Learning Systems Overview 1. Motivation - Why Graphical Models 2.
More informationBayesian Networks: Construction, Inference, Learning and Causal Interpretation. Volker Tresp Summer 2014
Bayesian Networks: Construction, Inference, Learning and Causal Interpretation Volker Tresp Summer 2014 1 Introduction So far we were mostly concerned with supervised learning: we predicted one or several
More informationCourse 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 informationThe Bayesian Brain. Robert Jacobs Department of Brain & Cognitive Sciences University of Rochester. May 11, 2017
The Bayesian Brain Robert Jacobs Department of Brain & Cognitive Sciences University of Rochester May 11, 2017 Bayesian Brain How do neurons represent the states of the world? How do neurons represent
More informationBack-propagation as reinforcement in prediction tasks
Back-propagation as reinforcement in prediction tasks André Grüning Cognitive Neuroscience Sector S.I.S.S.A. via Beirut 4 34014 Trieste Italy gruening@sissa.it Abstract. The back-propagation (BP) training
More informationRevealing inductive biases through iterated learning
Revealing inductive biases through iterated learning Tom Griffiths Department of Psychology Cognitive Science Program UC Berkeley with Mike Kalish, Brian Christian, Simon Kirby, Mike Dowman, Stephan Lewandowsky
More informationThe Kadir Operator Saliency, Scale and Image Description. Timor Kadir and Michael Brady University of Oxford
The Kadir Operator Saliency, Scale and Image Description Timor Kadir and Michael Brady University of Oxford 1 The issues salient standing out from the rest, noticeable, conspicous, prominent scale find
More informationComplexity of Representation and Inference in Compositional Models with Part Sharing
Journal of Machine Learning Research 17 (2016) 1-28 Submitted 7/13; Revised 5/15; Published 4/16 Complexity of Representation and Inference in Compositional Models with Part Sharing Alan Yuille Departments
More informationUnsupervised Learning of Invariant Representations in Hierarchical Architectures
Unsupervised Learning of nvariant Representations in Hierarchical Architectures Fabio Anselmi, Joel Z Leibo, Lorenzo Rosasco, Jim Mutch, Andrea Tacchetti, and Tomaso Poggio stituto taliano di Tecnologia,
More informationSum-Product Networks: A New Deep Architecture
Sum-Product Networks: A New Deep Architecture Pedro Domingos Dept. Computer Science & Eng. University of Washington Joint work with Hoifung Poon 1 Graphical Models: Challenges Bayesian Network Markov Network
More informationOn a model of visual cortex: learning invariance and selectivity Andrea Caponnetto,, Tomaso Poggio and, and Steve Smale
Computer Science and Artificial Intelligence Laboratory Technical Report MIT-CSAIL-TR-2008-030 CBCL-272 April 4, 2008 On a model of visual cortex: learning invariance and selectivity Andrea Caponnetto,,
More informationON THE TREATMENT AND CHALLENGES OF MODEL UNCERTAINTY
ON THE TREATMENT AND CHALLENGES OF MODEL UNCERTAINTY Enrique López Droguett Associate Professor Mechanical Engineering Department University of Chile elopezdroguett@ing.uchile.cl ROADMAP Fundamentals:
More informationArtificial Neural Network and Fuzzy Logic
Artificial Neural Network and Fuzzy Logic 1 Syllabus 2 Syllabus 3 Books 1. Artificial Neural Networks by B. Yagnanarayan, PHI - (Cover Topologies part of unit 1 and All part of Unit 2) 2. Neural Networks
More informationDenoising 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 informationNeural Nets in PR. Pattern Recognition XII. Michal Haindl. Outline. Neural Nets in PR 2
Neural Nets in PR NM P F Outline Motivation: Pattern Recognition XII human brain study complex cognitive tasks Michal Haindl Faculty of Information Technology, KTI Czech Technical University in Prague
More informationarxiv:physics/ v1 [physics.bio-ph] 19 Feb 1999
Odor recognition and segmentation by coupled olfactory bulb and cortical networks arxiv:physics/9902052v1 [physics.bioph] 19 Feb 1999 Abstract Zhaoping Li a,1 John Hertz b a CBCL, MIT, Cambridge MA 02139
More informationConvolutional neural networks
11-1: Convolutional neural networks Prof. J.C. Kao, UCLA Convolutional neural networks Motivation Biological inspiration Convolution operation Convolutional layer Padding and stride CNN architecture 11-2:
More informationThe XOR problem. Machine learning for vision. The XOR problem. The XOR problem. x 1 x 2. x 2. x 1. Fall Roland Memisevic
The XOR problem Fall 2013 x 2 Lecture 9, February 25, 2015 x 1 The XOR problem The XOR problem x 1 x 2 x 2 x 1 (picture adapted from Bishop 2006) It s the features, stupid It s the features, stupid The
More informationLooking forwards and backwards: Similarities and differences in prediction and retrodiction
Looking forwards and backwards: Similarities and differences in prediction and retrodiction Kevin A Smith (k2smith@ucsd.edu) and Edward Vul (evul@ucsd.edu) University of California, San Diego Department
More informationattention mechanisms and generative models
attention mechanisms and generative models Master's Deep Learning Sergey Nikolenko Harbour Space University, Barcelona, Spain November 20, 2017 attention in neural networks attention You re paying attention
More informationCOMPUTATIONAL MODELING OF VISUAL PERCEPTION
COMPUTATIONAL MODELING OF VISUAL PERCEPTION CSE6390D - PSYC6225A 3.0 (F) James Elder MW 13:00-14:30 Bethune 322 Enrolment limit: none Purpose: The goal of this course is to provide a framework and computational
More informationA Balanced Comparison of Object Invariances in Monkey IT Neurons
New Research Sensory and Motor Systems A Balanced Comparison of Object Invariances in Monkey IT Neurons N. Apurva Ratan Murty and Sripati P. Arun DOI:http://dx.doi.org/1.1523/ENEURO.333-16.217 Centre for
More informationSemi-supervised subspace analysis of human functional magnetic resonance imaging data
Max Planck Institut für biologische Kybernetik Max Planck Institute for Biological Cybernetics Technical Report No. 185 Semi-supervised subspace analysis of human functional magnetic resonance imaging
More informationCS540 Machine learning L9 Bayesian statistics
CS540 Machine learning L9 Bayesian statistics 1 Last time Naïve Bayes Beta-Bernoulli 2 Outline Bayesian concept learning Beta-Bernoulli model (review) Dirichlet-multinomial model Credible intervals 3 Bayesian
More informationUNIVERSITY OF CALIFORNIA, SAN DIEGO. Visual Recognition, Inference and Coding Using Learned Sparse Overcomplete Representations
UNIVERSITY OF CALIFORNIA, SAN DIEGO Visual Recognition, Inference and Coding Using Learned Sparse Overcomplete Representations A dissertation submitted in partial satisfaction of the requirements for the
More informationPosition Variance, Recurrence and Perceptual Learning
Position Variance, Recurrence and Perceptual Learning Zhaoping Li Peter Dayan Gatsby Computational Neuroscience Unit 7 Queen Square, London, England, WCN 3AR. zhaoping@gatsby.ucl.ac.uk dayan@gatsby.ucl.ac.uk
More informationSTA 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 informationBayesian Analysis. Bayesian Analysis: Bayesian methods concern one s belief about θ. [Current Belief (Posterior)] (Prior Belief) x (Data) Outline
Bayesian Analysis DuBois Bowman, Ph.D. Gordana Derado, M. S. Shuo Chen, M. S. Department of Biostatistics and Bioinformatics Center for Biomedical Imaging Statistics Emory University Outline I. Introduction
More informationEquivalence of Backpropagation and Contrastive Hebbian Learning in a Layered Network
LETTER Communicated by Geoffrey Hinton Equivalence of Backpropagation and Contrastive Hebbian Learning in a Layered Network Xiaohui Xie xhx@ai.mit.edu Department of Brain and Cognitive Sciences, Massachusetts
More informationPattern Recognition and Machine Learning
Christopher M. Bishop Pattern Recognition and Machine Learning ÖSpri inger Contents Preface Mathematical notation Contents vii xi xiii 1 Introduction 1 1.1 Example: Polynomial Curve Fitting 4 1.2 Probability
More informationDeep 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 informationHow to build a brain. Cognitive Modelling. Terry & Chris Centre for Theoretical Neuroscience University of Waterloo
How to build a brain Cognitive Modelling Terry & Chris Centre for Theoretical Neuroscience University of Waterloo So far... We have learned how to implement high-dimensional vector representations linear
More informationUncertainty, precision, prediction errors and their relevance to computational psychiatry
Uncertainty, precision, prediction errors and their relevance to computational psychiatry Christoph Mathys Wellcome Trust Centre for Neuroimaging at UCL, London, UK Max Planck UCL Centre for Computational
More informationNeural networks. Chapter 20, Section 5 1
Neural networks Chapter 20, Section 5 Chapter 20, Section 5 Outline Brains Neural networks Perceptrons Multilayer perceptrons Applications of neural networks Chapter 20, Section 5 2 Brains 0 neurons of
More information