Hierarchy. Will Penny. 24th March Hierarchy. Will Penny. Linear Models. Convergence. Nonlinear Models. References
|
|
- Eugene Porter
- 5 years ago
- Views:
Transcription
1 24th March 2011 Update
2 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 by Bayesian inference in a cortical hierarchy. y = W 1 x 1 + e 1 x 1 = W 2 x 2 + e 2 Update
3 The corresponding graphical model is The joint likelihood of data and model parameters is p(y, W 1, W 2, x 1, x 2 ) = p(y W 1, x 1 )p(w 1 )p(x 1 x 2, W 2 )p(w 2 )p(x 2 ) Update The first and second level prediction errors are assumed isotropic Gaussian with precisions λ 1 and λ 2. The priors over W 1 and W 2 are zero mean Gaussian, having isotropic covariances with precisions α 1 and α 2.
4 All parameters W 1, W 2, x 1 and x 2 are learnt by gradient ascent of the relevant part of the the joint likelihood. For example, for x 1 we have L(x 1 ) = log[p(y W 1, x 1 )p(x 1 x 2, W 2 )] as all other terms do not depend on x 1. Maximising this function will implicitly maximise the posterior probability p(x 1 y). Update
5 The joint log-likelihood as a function of first layer activity is L(x 1 ) = λ 1 2 (y ŷ)t (y ŷ) λ 2 2 (x 1 ˆx 1 ) T (x 1 ˆx 1 ) with image predictions ŷ = W 1 x 1 and predictions of first layer activity ˆx 1 = W 2 x 2 Update L(x 1 ) comprises precision weighted prediction error terms from both levels.
6 The activity is then updated by gradient ascent which gives τ x dx 1 dt τ x dx 1 dt = dl(x 1) dx 1 = λ 1 W T 1 (y W 1x 1 ) + λ 2 (ˆx 1 x 1 ) This is the same as online Bayesian learning for linear systems (last lecture). These updates have a simple predictive coding implementation. Update
7 Architecture Mumford (1992) I put forward a hypothesis on the role of the reciprocal, topographic pathways between two cortical areas, one often a higher area dealing with more abstract information about the world, the other lower dealing with more concrete data. The higher area attempts to fit its abstractions to the data it receives from lower areas by sending back to them from its deep pyramidal cells a template reconstruction best fitting the lower level view. The lower area attempts to reconcile the Update reconstruction of its view that it receives from higher areas with what it knows, sending back from its superficial pyramidal cells the features in its data which are not predicted by the higher area.
8 Update Update e 1 = y W 1 x 1 e 2 = x 1 W 2 x 2
9 Update τ x ẋ 1 = λ 1 W T 1 e 1 +λ 2 e 2 τ x ẋ 2 = λ 2 W T 2 e 2
10 Update τ w Ẇ 1 = λ 1 e 1 x T 1 α 1W 1 τ w Ẇ 2 = λ 2 e 2 x T 2 α 2W 2
11 Each second level unit effectively sees the whole image. Increasing Receptive Field Size In Rao and Ballard (1999) a Gaussian weighting was applied to the input of each first level node, so that it only sees a localised portion of the input image. Update
12 Increasing Receptive Field Size The images y (5 shown) are modelled with j = 1..3 first level modules with overlapping receptive fields. y j = W 1j x 1j + e 1 (256 1) = (256 32)(32 1) + (256 1) Each module is a linear expansion of a basis set W, with coefficients x which are different for each image. Each module predicts activity in a pixel patch. One can think of the ith row of W 1j as the projective field of the ith neuron in the jth module. And the ith entry in x 1j as the activity or firing rate of the ith neuron in the jth module. These coefficients are then constrained by a second level model Update x 1 = W 2 x 2 + e 2 (96 1) = (96 128)(128 1) + (96 1)
13 Update e 1j = y j W 1j x 1j e 2j = x 1j W 2j x 2 (j)
14 Update τ x ẋ 1j = λ 1 W T 1j e 1j + λ 2 e 2j
15 Update τ w Ẇ 1j = λ 1 e 1j x T 1j α 1 W 1j
16 Receptive Fields Level 1 receptive fields are reminiscent of Difference-of-Gaussian (DOG) filters that have been used to model simple-cell RFs in primary visual cortex. Update Level 2 cells respond to more complex features.
17 Update The response of level-1 prediction error units diminishes for bars that go beyond the end of each level-1 receptive field. So-called end stopping.
18 Error unit activity naturally arises from difference in bottom-up activity and top down predictions. Update The network was trained on natural images for which short bars seldom occur in isolation. Short bars are generally part of longer bars.
19 End Stopping disappears if feedback in the model is disabled or if layer 6 activity is inactivated in squirrel monkey (Sandell and Schiller, 1982). Update
20 Nonlinear models Friston (2003) considers nonlinear hierarchical models of the form x 1 = g(x 2, w 1 ) + e 1 x 2 = g(x 3, w 2 ) + e 2.. =.. x R 1 = g(x R, w R 1 ) + e R 1 where y = x 1 is the observed data, g(x i+1, w i ) is some nonlinear function of hidden causes x i+1 and parameters w i, and e i is zero mean additive Gaussian noise with covariance C i and i indexes the level in the hierarchy. C i is parameterised by λ i. These equations embody structural priors. The generative model is not dynamic. The recognition model is. Update
21 There are no priors over w or λ. Update The joint probability of activities in all regions r = 1..R is therefore R p(x w, λ) = p(x i x i+1, w i, λ i ) = i=1 R N(x i ; g(x i+1, w i ), C i ) i=1
22 Joint Log Likelihood The joint log likelihood is L(x, w, λ) = R log p(x i x i+1, w i, λ i ) i=1 This can be written as (dropping constant terms) L(x, w, λ) = R i=1 ( 1 2 et i e i 1 ) 2 log C i where the prediction errors are given by Update e i = C 1/2 i [x i g i (x i+1, w i )] The hidden causes, parameters and variance components can be estimated using a gradient ascent scheme to find their MAP values.
23 In the univariate case, if the error covariances have the form C 1/2 i = 1 + λ i then the prediction errors can be written. The last term acts as a decay with time constant λ i. Hence e i = (1 + λ i ) 1 [x i g(x i+1, w i )] Rearranging gives Update e i = [x i g(x i+1, w i )] λ i e i
24 The joint log-likelihood is where Hence so dl(x i ) x i L(x) = i 1 2 et i e i +... e i = (1 + λ i ) 1 [x i g(x i+1, w i )] L(x i ) = 1 2 et i 1 e i et i e i = ( dei 1 dx i ) T ( ) T dei e i 1 e i dx i Update
25 For the hidden causes we have Update τ x ẋ i = dl dx i = ( ) T ( ) T dei 1 dei e i 1 dx e i i dx i The first term is instantiated via forward recognition effects and the second term via lateral connections. These lateral connections embody the prior at each level. Connections are reciprocal.
26 Top-down synapses For the top-down connections we have Update τ w w i = dl dw i = ( ) T dei e i dw i This reduces to Hebbian learning for linear models τ w ẇ i = (1 + λ i )e i x i+1
27 Recurrent synapses on error units For the variance components τ λ λ i = dl dλ i = < ( ) T dei e i > 1 dλ i 1 + λ i Update The self-connections whiten the errors τ λ λi = (1 + λ i ) 1 (e i e T i 1)
28 K. Friston (2003) Learning and inference in the brain. Neural Networks 16, M. Mesulam (1998) From sensation to cognition. Brain (121), D. Mumford (1992) On the computational architecture of the neocortex II The role of cortico-cortical loops. Biological Cybernetics 66, R. Rao and D. Ballard (1999) Nature Neuroscience 2, Update G. Shepherd (2004). The Synaptic Organisation of the Brain. Oxford.
Principles of DCM. Will Penny. 26th May Principles of DCM. Will Penny. Introduction. Differential Equations. Bayesian Estimation.
26th May 2011 Dynamic Causal Modelling Dynamic Causal Modelling is a framework studying large scale brain connectivity by fitting differential equation models to brain imaging data. DCMs differ in their
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 informationConvolutional networks. Sebastian Seung
Convolutional networks Sebastian Seung Convolutional network Neural network with spatial organization every neuron has a location usually on a grid Translation invariance synaptic strength depends on locations
More informationNatural Image Statistics
Natural Image Statistics A probabilistic approach to modelling early visual processing in the cortex Dept of Computer Science Early visual processing LGN V1 retina From the eye to the primary visual cortex
More informationFirst Technical Course, European Centre for Soft Computing, Mieres, Spain. 4th July 2011
First Technical Course, European Centre for Soft Computing, Mieres, Spain. 4th July 2011 Linear Given probabilities p(a), p(b), and the joint probability p(a, B), we can write the conditional probabilities
More informationHigher Order Statistics
Higher Order Statistics Matthias Hennig Neural Information Processing School of Informatics, University of Edinburgh February 12, 2018 1 0 Based on Mark van Rossum s and Chris Williams s old NIP slides
More informationEmergence of Phase- and Shift-Invariant Features by Decomposition of Natural Images into Independent Feature Subspaces
LETTER Communicated by Bartlett Mel Emergence of Phase- and Shift-Invariant Features by Decomposition of Natural Images into Independent Feature Subspaces Aapo Hyvärinen Patrik Hoyer Helsinki University
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 informationChris Bishop s PRML Ch. 8: Graphical Models
Chris Bishop s PRML Ch. 8: Graphical Models January 24, 2008 Introduction Visualize the structure of a probabilistic model Design and motivate new models Insights into the model s properties, in particular
More informationNonlinear reverse-correlation with synthesized naturalistic noise
Cognitive Science Online, Vol1, pp1 7, 2003 http://cogsci-onlineucsdedu Nonlinear reverse-correlation with synthesized naturalistic noise Hsin-Hao Yu Department of Cognitive Science University of California
More informationHow 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 informationNONLINEAR CLASSIFICATION AND REGRESSION. J. Elder CSE 4404/5327 Introduction to Machine Learning and Pattern Recognition
NONLINEAR CLASSIFICATION AND REGRESSION Nonlinear Classification and Regression: Outline 2 Multi-Layer Perceptrons The Back-Propagation Learning Algorithm Generalized Linear Models Radial Basis Function
More informationBayesian probability theory and generative models
Bayesian probability theory and generative models Bruno A. Olshausen November 8, 2006 Abstract Bayesian probability theory provides a mathematical framework for peforming inference, or reasoning, using
More informationBayesian Inference Course, WTCN, UCL, March 2013
Bayesian Course, WTCN, UCL, March 2013 Shannon (1948) asked how much information is received when we observe a specific value of the variable x? If an unlikely event occurs then one would expect the information
More information(Feed-Forward) Neural Networks Dr. Hajira Jabeen, Prof. Jens Lehmann
(Feed-Forward) Neural Networks 2016-12-06 Dr. Hajira Jabeen, Prof. Jens Lehmann Outline In the previous lectures we have learned about tensors and factorization methods. RESCAL is a bilinear model for
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 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 informationLecture 4: Feed Forward Neural Networks
Lecture 4: Feed Forward Neural Networks Dr. Roman V Belavkin Middlesex University BIS4435 Biological neurons and the brain A Model of A Single Neuron Neurons as data-driven models Neural Networks Training
More informationLecture 2: From Linear Regression to Kalman Filter and Beyond
Lecture 2: From Linear Regression to Kalman Filter and Beyond January 18, 2017 Contents 1 Batch and Recursive Estimation 2 Towards Bayesian Filtering 3 Kalman Filter and Bayesian Filtering and Smoothing
More informationSean Escola. Center for Theoretical Neuroscience
Employing hidden Markov models of neural spike-trains toward the improved estimation of linear receptive fields and the decoding of multiple firing regimes Sean Escola Center for Theoretical Neuroscience
More informationWill Penny. 21st April The Macroscopic Brain. Will Penny. Cortical Unit. Spectral Responses. Macroscopic Models. Steady-State Responses
The The 21st April 2011 Jansen and Rit (1995), building on the work of Lopes Da Sliva and others, developed a biologically inspired model of EEG activity. It was originally developed to explain alpha activity
More informationLecture 2: From Linear Regression to Kalman Filter and Beyond
Lecture 2: From Linear Regression to Kalman Filter and Beyond Department of Biomedical Engineering and Computational Science Aalto University January 26, 2012 Contents 1 Batch and Recursive Estimation
More informationHow 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 informationDecoding conceptual representations
Decoding conceptual representations!!!! Marcel van Gerven! Computational Cognitive Neuroscience Lab (www.ccnlab.net) Artificial Intelligence Department Donders Centre for Cognition Donders Institute for
More informationBasic 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 informationInternal Covariate Shift Batch Normalization Implementation Experiments. Batch Normalization. Devin Willmott. University of Kentucky.
Batch Normalization Devin Willmott University of Kentucky October 23, 2017 Overview 1 Internal Covariate Shift 2 Batch Normalization 3 Implementation 4 Experiments Covariate Shift Suppose we have two distributions,
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 informationMachine Learning for Large-Scale Data Analysis and Decision Making A. Neural Networks Week #6
Machine Learning for Large-Scale Data Analysis and Decision Making 80-629-17A Neural Networks Week #6 Today Neural Networks A. Modeling B. Fitting C. Deep neural networks Today s material is (adapted)
More informationMultivariate Bayesian Linear Regression MLAI Lecture 11
Multivariate Bayesian Linear Regression MLAI Lecture 11 Neil D. Lawrence Department of Computer Science Sheffield University 21st October 2012 Outline Univariate Bayesian Linear Regression Multivariate
More informationCSE/NB 528 Final Lecture: All Good Things Must. CSE/NB 528: Final Lecture
CSE/NB 528 Final Lecture: All Good Things Must 1 Course Summary Where have we been? Course Highlights Where do we go from here? Challenges and Open Problems Further Reading 2 What is the neural code? What
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 informationTHE retina in general consists of three layers: photoreceptors
CS229 MACHINE LEARNING, STANFORD UNIVERSITY, DECEMBER 2016 1 Models of Neuron Coding in Retinal Ganglion Cells and Clustering by Receptive Field Kevin Fegelis, SUID: 005996192, Claire Hebert, SUID: 006122438,
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 informationAnnealed Importance Sampling for Neural Mass Models
for Neural Mass Models, UCL. WTCN, UCL, October 2015. Generative Model Behavioural or imaging data y. Likelihood p(y w, Γ). We have a Gaussian prior over model parameters p(w µ, Λ) = N (w; µ, Λ) Assume
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 informationMachine 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 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 Concept Learning
Learning from positive and negative examples Bayesian Concept Learning Chen Yu Indiana University With both positive and negative examples, it is easy to define a boundary to separate these two. Just with
More informationDynamic Causal Modelling for fmri
Dynamic Causal Modelling for fmri André Marreiros Friday 22 nd Oct. 2 SPM fmri course Wellcome Trust Centre for Neuroimaging London Overview Brain connectivity: types & definitions Anatomical connectivity
More informationArtificial Neural Networks
Artificial Neural Networks Stephan Dreiseitl University of Applied Sciences Upper Austria at Hagenberg Harvard-MIT Division of Health Sciences and Technology HST.951J: Medical Decision Support Knowledge
More informationOptimal In-Place Self-Organization for Cortical Development: Limited Cells, Sparse Coding and Cortical Topography
Optimal In-Place Self-Organization for Cortical Development: Limited Cells, Sparse Coding and Cortical Topography Juyang Weng and Matthew D. Luciw Department of Computer Science and Engineering Michigan
More informationCheng Soon Ong & Christian Walder. Canberra February June 2018
Cheng Soon Ong & Christian Walder Research Group and College of Engineering and Computer Science Canberra February June 218 Outlines Overview Introduction Linear Algebra Probability Linear Regression 1
More informationNeural Networks. Textbook. Other Textbooks and Books. Course Info. (click on
636-600 Neural Networks Textbook Instructor: Yoonsuck Choe Contact info: HRBB 322B, 45-5466, choe@tamu.edu Web page: http://faculty.cs.tamu.edu/choe Simon Haykin, Neural Networks: A Comprehensive Foundation,
More informationIs early vision optimised for extracting higher order dependencies? Karklin and Lewicki, NIPS 2005
Is early vision optimised for extracting higher order dependencies? Karklin and Lewicki, NIPS 2005 Richard Turner (turner@gatsby.ucl.ac.uk) Gatsby Computational Neuroscience Unit, 02/03/2006 Outline Historical
More informationLecture 4: State Estimation in Hidden Markov Models (cont.)
EE378A Statistical Signal Processing Lecture 4-04/13/2017 Lecture 4: State Estimation in Hidden Markov Models (cont.) Lecturer: Tsachy Weissman Scribe: David Wugofski In this lecture we build on previous
More informationDATA MINING AND MACHINE LEARNING. Lecture 4: Linear models for regression and classification Lecturer: Simone Scardapane
DATA MINING AND MACHINE LEARNING Lecture 4: Linear models for regression and classification Lecturer: Simone Scardapane Academic Year 2016/2017 Table of contents Linear models for regression Regularized
More informationRegression. Machine Learning and Pattern Recognition. Chris Williams. School of Informatics, University of Edinburgh.
Regression Machine Learning and Pattern Recognition Chris Williams School of Informatics, University of Edinburgh September 24 (All of the slides in this course have been adapted from previous versions
More informationCheng Soon Ong & Christian Walder. Canberra February June 2018
Cheng Soon Ong & Christian Walder Research Group and College of Engineering and Computer Science Canberra February June 2018 (Many figures from C. M. Bishop, "Pattern Recognition and ") 1of 254 Part V
More informationLecture 6: Bayesian Inference in SDE Models
Lecture 6: Bayesian Inference in SDE Models Bayesian Filtering and Smoothing Point of View Simo Särkkä Aalto University Simo Särkkä (Aalto) Lecture 6: Bayesian Inference in SDEs 1 / 45 Contents 1 SDEs
More informationDo neural models scale up to a human brain?
Do neural models scale up to a human brain? Roman V. Belavkin (r.belavkin@mdx.ac.uk) School of Computing Science, Middlesex University, London NW4 4BT, UK August 27, 2007 oman Belavkin, Middlesex University,
More informationNeural Coding: Integrate-and-Fire Models of Single and Multi-Neuron Responses
Neural Coding: Integrate-and-Fire Models of Single and Multi-Neuron Responses Jonathan Pillow HHMI and NYU http://www.cns.nyu.edu/~pillow Oct 5, Course lecture: Computational Modeling of Neuronal Systems
More informationATTRACTORS IN SONG. KARL FRISTON and STEFAN KIEBEL
Attractors in song: 1 New Mathematics and Natural Computation Vol. 5, No. 1 (9) 1-3 World Scientific Publishing Company ATTRACTORS IN SONG KARL FRISTON and STEFAN KIEBEL The Wellcome Trust Centre of Neuroimaging
More informationInformatics 2B: Learning and Data Lecture 10 Discriminant functions 2. Minimal misclassifications. Decision Boundaries
Overview Gaussians estimated from training data Guido Sanguinetti Informatics B Learning and Data Lecture 1 9 March 1 Today s lecture Posterior probabilities, decision regions and minimising the probability
More informationAn EM algorithm for Gaussian Markov Random Fields
An EM algorithm for Gaussian Markov Random Fields Will Penny, Wellcome Department of Imaging Neuroscience, University College, London WC1N 3BG. wpenny@fil.ion.ucl.ac.uk October 28, 2002 Abstract Lavine
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 information11. Learning graphical models
Learning graphical models 11-1 11. Learning graphical models Maximum likelihood Parameter learning Structural learning Learning partially observed graphical models Learning graphical models 11-2 statistical
More informationAn Adaptive Bayesian Network for Low-Level Image Processing
An Adaptive Bayesian Network for Low-Level Image Processing S P Luttrell Defence Research Agency, Malvern, Worcs, WR14 3PS, UK. I. INTRODUCTION Probability calculus, based on the axioms of inference, Cox
More informationBayesian Methods for Sparse Signal Recovery
Bayesian Methods for Sparse Signal Recovery Bhaskar D Rao 1 University of California, San Diego 1 Thanks to David Wipf, Jason Palmer, Zhilin Zhang and Ritwik Giri Motivation Motivation Sparse Signal Recovery
More informationDynamic Modeling of Brain Activity
0a Dynamic Modeling of Brain Activity EIN IIN PC Thomas R. Knösche, Leipzig Generative Models for M/EEG 4a Generative Models for M/EEG states x (e.g. dipole strengths) parameters parameters (source positions,
More informationLinear Models for Regression
Linear Models for Regression Seungjin Choi Department of Computer Science and Engineering Pohang University of Science and Technology 77 Cheongam-ro, Nam-gu, Pohang 37673, Korea seungjin@postech.ac.kr
More informationBACKPROPAGATION. Neural network training optimization problem. Deriving backpropagation
BACKPROPAGATION Neural network training optimization problem min J(w) w The application of gradient descent to this problem is called backpropagation. Backpropagation is gradient descent applied to J(w)
More informationData assimilation with and without a model
Data assimilation with and without a model Tim Sauer George Mason University Parameter estimation and UQ U. Pittsburgh Mar. 5, 2017 Partially supported by NSF Most of this work is due to: Tyrus Berry,
More informationCSC 411 Lecture 10: Neural Networks
CSC 411 Lecture 10: Neural Networks Roger Grosse, Amir-massoud Farahmand, and Juan Carrasquilla University of Toronto UofT CSC 411: 10-Neural Networks 1 / 35 Inspiration: The Brain Our brain has 10 11
More informationProbabilistic & Unsupervised Learning
Probabilistic & Unsupervised Learning Gaussian Processes Maneesh Sahani maneesh@gatsby.ucl.ac.uk Gatsby Computational Neuroscience Unit, and MSc ML/CSML, Dept Computer Science University College London
More informationarxiv: v1 [q-bio.nc] 4 Jan 2016
Nonlinear Hebbian learning as a unifying principle in receptive field formation Carlos S. N. Brito*, Wulfram Gerstner arxiv:1601.00701v1 [q-bio.nc] 4 Jan 2016 School of Computer and Communication Sciences
More informationLateral organization & computation
Lateral organization & computation review Population encoding & decoding lateral organization Efficient representations that reduce or exploit redundancy Fixation task 1rst order Retinotopic maps Log-polar
More informationCHARACTERIZATION OF NONLINEAR NEURON RESPONSES
CHARACTERIZATION OF NONLINEAR NEURON RESPONSES Matt Whiteway whit8022@umd.edu Dr. Daniel A. Butts dab@umd.edu Neuroscience and Cognitive Science (NACS) Applied Mathematics and Scientific Computation (AMSC)
More informationModel Comparison. Course on Bayesian Inference, WTCN, UCL, February Model Comparison. Bayes rule for models. Linear Models. AIC and BIC.
Course on Bayesian Inference, WTCN, UCL, February 2013 A prior distribution over model space p(m) (or hypothesis space ) can be updated to a posterior distribution after observing data y. This is implemented
More informationModel of a Biological Neuron as a Temporal Neural Network
Model of a Biological Neuron as a Temporal Neural Network Sean D. Murphy and Edward W. Kairiss Interdepartmental Neuroscience Program, Department of Psychology, and The Center for Theoretical and Applied
More informationClassification goals: Make 1 guess about the label (Top-1 error) Make 5 guesses about the label (Top-5 error) No Bounding Box
ImageNet Classification with Deep Convolutional Neural Networks Alex Krizhevsky, Ilya Sutskever, Geoffrey E. Hinton Motivation Classification goals: Make 1 guess about the label (Top-1 error) Make 5 guesses
More informationSTA 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 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 informationComputational statistics
Computational statistics Lecture 3: Neural networks Thierry Denœux 5 March, 2016 Neural networks A class of learning methods that was developed separately in different fields statistics and artificial
More informationPATTERN RECOGNITION AND MACHINE LEARNING CHAPTER 13: SEQUENTIAL DATA
PATTERN RECOGNITION AND MACHINE LEARNING CHAPTER 13: SEQUENTIAL DATA Contents in latter part Linear Dynamical Systems What is different from HMM? Kalman filter Its strength and limitation Particle Filter
More informationChapter 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 informationDropout as a Bayesian Approximation: Insights and Applications
Dropout as a Bayesian Approximation: Insights and Applications Yarin Gal and Zoubin Ghahramani Discussion by: Chunyuan Li Jan. 15, 2016 1 / 16 Main idea In the framework of variational inference, the authors
More informationIntelligent Control. Module I- Neural Networks Lecture 7 Adaptive Learning Rate. Laxmidhar Behera
Intelligent Control Module I- Neural Networks Lecture 7 Adaptive Learning Rate Laxmidhar Behera Department of Electrical Engineering Indian Institute of Technology, Kanpur Recurrent Networks p.1/40 Subjects
More informationVariational Inference (11/04/13)
STA561: Probabilistic machine learning Variational Inference (11/04/13) Lecturer: Barbara Engelhardt Scribes: Matt Dickenson, Alireza Samany, Tracy Schifeling 1 Introduction In this lecture we will further
More informationDeep Feedforward Networks
Deep Feedforward Networks Liu Yang March 30, 2017 Liu Yang Short title March 30, 2017 1 / 24 Overview 1 Background A general introduction Example 2 Gradient based learning Cost functions Output Units 3
More informationGatsby Theoretical Neuroscience Lectures: Non-Gaussian statistics and natural images Parts I-II
Gatsby Theoretical Neuroscience Lectures: Non-Gaussian statistics and natural images Parts I-II Gatsby Unit University College London 27 Feb 2017 Outline Part I: Theory of ICA Definition and difference
More informationLearning Gaussian Process Models from Uncertain Data
Learning Gaussian Process Models from Uncertain Data Patrick Dallaire, Camille Besse, and Brahim Chaib-draa DAMAS Laboratory, Computer Science & Software Engineering Department, Laval University, Canada
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 informationLogistic Regression Review Fall 2012 Recitation. September 25, 2012 TA: Selen Uguroglu
Logistic Regression Review 10-601 Fall 2012 Recitation September 25, 2012 TA: Selen Uguroglu!1 Outline Decision Theory Logistic regression Goal Loss function Inference Gradient Descent!2 Training Data
More informationUsing Variable Threshold to Increase Capacity in a Feedback Neural Network
Using Variable Threshold to Increase Capacity in a Feedback Neural Network Praveen Kuruvada Abstract: The article presents new results on the use of variable thresholds to increase the capacity of a feedback
More informationOrganization. I MCMC discussion. I project talks. I Lecture.
Organization I MCMC discussion I project talks. I Lecture. Content I Uncertainty Propagation Overview I Forward-Backward with an Ensemble I Model Reduction (Intro) Uncertainty Propagation in Causal Systems
More information+ + ( + ) = Linear recurrent networks. Simpler, much more amenable to analytic treatment E.g. by choosing
Linear recurrent networks Simpler, much more amenable to analytic treatment E.g. by choosing + ( + ) = Firing rates can be negative Approximates dynamics around fixed point Approximation often reasonable
More informationComputational Cognitive Science
Computational Cognitive Science Lecture 9: A Bayesian model of concept learning Chris Lucas School of Informatics University of Edinburgh October 16, 218 Reading Rules and Similarity in Concept Learning
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 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 informationA Monte Carlo Sequential Estimation for Point Process Optimum Filtering
2006 International Joint Conference on Neural Networks Sheraton Vancouver Wall Centre Hotel, Vancouver, BC, Canada July 16-21, 2006 A Monte Carlo Sequential Estimation for Point Process Optimum Filtering
More informationStatistical Machine Learning (BE4M33SSU) Lecture 5: Artificial Neural Networks
Statistical Machine Learning (BE4M33SSU) Lecture 5: Artificial Neural Networks Jan Drchal Czech Technical University in Prague Faculty of Electrical Engineering Department of Computer Science Topics covered
More informationExpectation Propagation Algorithm
Expectation Propagation Algorithm 1 Shuang Wang School of Electrical and Computer Engineering University of Oklahoma, Tulsa, OK, 74135 Email: {shuangwang}@ou.edu This note contains three parts. First,
More informationLoopSOM: A Robust SOM Variant Using Self-Organizing Temporal Feedback Connections
LoopSOM: A Robust SOM Variant Using Self-Organizing Temporal Feedback Connections Rafael C. Pinto, Paulo M. Engel Instituto de Informática Universidade Federal do Rio Grande do Sul (UFRGS) P.O. Box 15.064
More informationVariational Autoencoders
Variational Autoencoders Recap: Story so far A classification MLP actually comprises two components A feature extraction network that converts the inputs into linearly separable features Or nearly linearly
More informationLecture 17: Neural Networks and Deep Learning
UVA CS 6316 / CS 4501-004 Machine Learning Fall 2016 Lecture 17: Neural Networks and Deep Learning Jack Lanchantin Dr. Yanjun Qi 1 Neurons 1-Layer Neural Network Multi-layer Neural Network Loss Functions
More informationProbabilistic Reasoning in Deep Learning
Probabilistic Reasoning in Deep Learning Dr Konstantina Palla, PhD palla@stats.ox.ac.uk September 2017 Deep Learning Indaba, Johannesburgh Konstantina Palla 1 / 39 OVERVIEW OF THE TALK Basics of Bayesian
More informationIntroduction to Probabilistic Graphical Models
Introduction to Probabilistic Graphical Models Sargur Srihari srihari@cedar.buffalo.edu 1 Topics 1. What are probabilistic graphical models (PGMs) 2. Use of PGMs Engineering and AI 3. Directionality in
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 information