Probabilistic Models in Theoretical Neuroscience
|
|
- Nathaniel Logan
- 6 years ago
- Views:
Transcription
1 Probabilistic Models in Theoretical Neuroscience visible unit Boltzmann machine semi-restricted Boltzmann machine restricted Boltzmann machine hidden unit Neural models of probabilistic sampling: introduction Matt Graham 16 th January 2014
2 Overview 1 Motivation What is the neural sampling hypothesis? Why is it interesting? Toy example 2 Theory review Stochastic networks Why sigmoidal conditionals? Boltzmann machines 3 Neural dynamics as sampling Introduction Overview of model Simulations 4 More recent work
3 Overview 1 Motivation What is the neural sampling hypothesis? Why is it interesting? Toy example 2 Theory review Stochastic networks Why sigmoidal conditionals? Boltzmann machines 3 Neural dynamics as sampling Introduction Overview of model Simulations 4 More recent work
4 Neural sampling hypothesis Model for probabilistic perception and learning. Proposes activity patterns across networks of neurons represent samples from posterior distribution over interpretations given input. Neural response variability uncertainty in interpretation of inputs. Spontaneous network activity samples from prior distribution over inputs and interpretations. Some experimental support from systematic variation in response variability, high degree of structure in spontaneous network activity and similarity to stimulus evoked activity.
5 Computational advantages (I) Anytime computing y 2 Increasing accuracy y 2 Decreasing time y 1 y 1
6 Computational advantages (II) Marginalisation at no extra cost y 2 y 1
7 Computational advantages (III) Consistency of representation distinction between input and output arbitrary hierarchical and recurrent models learning from examples naturally deals with incomplete input
8 Toy example Is a 'o' Is a 'b' Is a 'o' Is a '6' Is a '6' Is a 'b'
9 Toy example Is a 'o' Is a 'b' Is a 'o' Is a '6' Is a '6' Is a 'b'
10 Toy example Next to digits Is a 'o' Is a 'b' Is a 'o' Next to digits Is a '6' Is a '6' Is a 'b'
11 Overview 1 Motivation What is the neural sampling hypothesis? Why is it interesting? Toy example 2 Theory review Stochastic networks Why sigmoidal conditionals? Boltzmann machines 3 Neural dynamics as sampling Introduction Overview of model Simulations 4 More recent work
12 Stochastic binary neural network models Spiking point neuron models. Inter-neuron communication assumed to be entirely spike based (binary). Neural spiking stochastic - network dynamics define probability of each neuron firing given current state of network. Typically discrete time models - time binned into small intervals and network state defined as set of binary variables indicating if neurons fired in last interval or not.
13 General sigmoidal stochastic binary network (SSBN) Network of N binary neurons, states s = [s i ] i {1...N} {0, 1} N Parametrised by: weight matrix W = [w ij ] i,j {1...N} R N N bias vector b = [b i ] i {1...N} R N Local potential weighted sum of states of other units N ( ) u (t) i = w ij s (t) j + b i j=1 If unit i updated at t + 1, new state sampled from conditional P ( s (t+1) i = 1 s (t)) ( = σ u (t) i ) = e u(t) i Special case of more general Markov random field. σ(u) u
14 A brief aside Is there any biological justification for using sigmoidal conditional distributions? (Yes)
15 Origins of stochasticity in biological neurons For a fixed injected current signal neural firing tends to be highly consistent Variability appears to mainly arise from synaptic transmission Number and transmitter content of synaptic vesicles released on arrival of a presynaptic spike both fluctuate Figure source: Mainen and Sejnowski (1995)
16 Synaptic noise model (I) Number of vesicles released Poisson distribution. Transmitter content of each vesicle Gaussian distribution. Figure source: Castillo and Katz (1954)
17 y Motivation Theory review Neural dynamics as sampling More recent work Synaptic noise model (II) y =Φ(x) y =σ( πx) x Assumption of independent distributions and large number of synaptic connections Central limit theorem conditional distribution on membrane potential given spiking state of rest of network Gaussian. conditional probability of neuron being super threshold and so spiking takes form of Gaussian CDF. Gaussian CDF Φ(x) well approximated by scaled sigmoid σ(x) = [1 + exp( x)] 1.
18 Boltzmann machines (BM) visible unit Boltzmann machine semi-restricted Boltzmann machine restricted Boltzmann machine hidden unit Analytically tractable variant of SSBN. Also known as an Ising model within statistical physics. Constrained to have symmetric connectivity (w ij = w ji i, j) and zero self-connectivity (w ii = 0 i). Visible units are fixed to known values, hidden units are freely varying. Restricted and semi-restricted BMs are special cases of general BM with restricted connectivity graphs allowing simpler updates.
19 Boltzmann machine dynamics Each time-step a single unit picked to update, either deterministic sequence or randomly (Gibbs sampling). Symmetric connectivity enforces detailed balance condition i.e. that transitions are reversible, guaranteeing existence of equilibrium distribution. ( ) ( ) P P s (t) = u ( s (t+1) = v P s (t+1) = v s (t) = u = ) ( ) P s (t) = u s (t+1) = v After initial burn in, dynamics of network cause it to sample from Boltzmann distribution at equilibrium P (s) = 1 Z exp ( E(s)) = 1 ( ) 1 Z exp 2 st Ws + b T s
20 Boltzmann machine learning Boltzmann machines can be trained so that the equilibrium distribution tends towards any arbitrary distribution across binary vectors given samples from that distribution 1. Log likelihood derivative (s = [ s T h s T ] T) v log [P (s v )] w ij = s h {s i s j P (s h s v )} s = s i s j + s i s j {s i s j P (s)} Expectations generally analytically intractable approximated with MCMC sampling based methods. Learning rule is local & Hebbian-like biologically plausible. For large networks, learning very slow due to need to allow network to converge to equilibrium distribution. 1 Ackley, Hinton and Sejnowski (1985)
21 Parallel updates and asymmetric connectivity Updating all units in parallel but maintaining symmetric connectivity gives different but still tractable equilibrium distribution and learning rule 2. Relaxing symmetry constraint generally means no longer tractable to find analytic form for stationary distribution and possible there will be none if Markov chain non-ergodic. Irreversibility introduced by weight asymmetry may however improve speed of convergence to stationary distribution while also being more biologically relevant. Learning rule can still be derived using time-dependent state distribution but this introduces requirement to take expectations over history of states 3. 2 Apolloni and de Falco (1990) 3 Apolloni, Bertoni, Campadelli and de Falco (1991)
22 Boltzmann machines as a model for cortical computation + Distributed computation + Binary communication between units + High representational power + Local learning rule - Discrete time formulation - Reversible dynamics - Symmetric connectivity - Slow convergence
23 Boltzmann machines as a model for cortical computation + Distributed computation + Binary communication between units + High representational power + Local learning rule - Discrete time formulation - Reversible dynamics - Symmetric connectivity - Slow convergence
24 Overview 1 Motivation What is the neural sampling hypothesis? Why is it interesting? Toy example 2 Theory review Stochastic networks Why sigmoidal conditionals? Boltzmann machines 3 Neural dynamics as sampling Introduction Overview of model Simulations 4 More recent work
25 Neural Dynamics as Sampling: A model for stochastic computation in recurrent networks of spiking neurons L. Buesing, J. Bill, B. Nessler and W. Maass - PLOS Computational Biology (2011) Demonstrates a network model with more biologically plausible dynamics than a BM which samples from a Boltzmann distribution. Consists of a recurrently connected network of spiking neurons with irreversible dynamics. Irreversible dynamics allow inclusion of refractory mechanism and finite duration post-synaptic potentials. Discrete time models with both absolute and relative refractory mechanisms demonstrated. Continuous time formulation shown as a limiting-case of discrete time dynamics.
26 Relation between spike activity and network state k ζ k [t] z k [t] t-τ t Network state defined by ζ[t] = [ζ 1 [t]... ζ N [t]] T with Markov property P (ζ[t + 1] ζ[t], ζ[t 1],...) = P (ζ[t + 1] ζ[t]) Here τ = absolute refractory period = PSP duration
27 Discrete time model with absolute refractory mechanism for k = 1 to N: if ζ k [t] > 1: ζ k [t] = ζ k [t 1] 1 else: u k = N j=1 (w kjz j [t]) + b k r rand(0, 1) z k [t] = r σ(u k log τ) if z k [t] = 1: ζ k [t] = τ else: ζ k [t] = 0
28 Discrete time model with relative refractory mechanism Relaxes assumption of hard refractory period with no firing. Probability of any neuron firing defined as product of functions of last firing time and membrane potential P (z k [t] = 1 ζ k [t 1], u k [t 1]) = f (u k [t 1]) g (ζ k [t 1])
29 Sampling from random distributions with relative refractory mechanism
30 Effect of using more realistic post-synaptic potentials
31 Toy model of perceptual multistability
32 Overview 1 Motivation What is the neural sampling hypothesis? Why is it interesting? Toy example 2 Theory review Stochastic networks Why sigmoidal conditionals? Boltzmann machines 3 Neural dynamics as sampling Introduction Overview of model Simulations 4 More recent work
33 Bayesian computation emerges in generic cortical microcircuits through spike-timing-dependent plasticity B. Nessler, M. Pfeiffer, L. Buesing and W. Maass - PLOS Computational Biology (2013) Proposes biologically plausible probabilistic learning rule Spike timing dependent plasticity updates within soft winner take all cortical microcircuits shown to approximate expectation maximisation Limited to single layer networks in this paper, proposes potentially could be extended to deep and/or recurrent structures
34 Stochastic Computations in Cortical Microcircuit Models S. Habenschuss, Z. Jonke and W Maass - PLOS Computational Biology (2013) Shows that under quite general conditions, the activity of a network of neurons with some degree of stochasticity in dynamics will converge to a stationary distribution Oscillatory input / activity shown to lead to phase specific stationary distributions. Simulations performed with cortical microcircuit model with anatomically based laminar structure with separate inhibitory / excitatory populations and data-based network connectivity and short-term dynamics.
35 Thank you - any questions? References Mainen, Z. F., & Sejnowski, T. J. (1995). Reliability of spike timing in neocortical neurons. Science, 268(5216), Del Castillo, J., & Katz, B. (1954). Quantal components of the end-plate potential. The Journal of physiology, 124(3), Ackley, D., Hinton, G., and Sejnowski, T. (1985). A Learning Algorithm for Boltzmann Machines. Cognitive Science, 9(1): Apolloni, B., & de Falco, D. (1991). Learning by parallel Boltzmann machines. Information Theory, IEEE Transactions on, 37(4), Apolloni, B., Bertoni, A., Campadelli, P., & de Falco, D. (1991). Asymmetric Boltzmann machines. Biological cybernetics, 66(1), Buesing, L., Bill, J., Nessler, B., & Maass, W. (2011). Neural dynamics as sampling: A model for stochastic computation in recurrent networks of spiking neurons. PLoS computational biology, 7(11), e Resources Kappen, H. J. (2001). An introduction to stochastic neural networks. Handbook of Biological Physics, 4, Hinton, G. H. (2007) Boltzmann machine. Scholarpedia, 2(5):1668.
Modelling stochastic neural learning
Modelling stochastic neural learning Computational Neuroscience András Telcs telcs.andras@wigner.mta.hu www.cs.bme.hu/~telcs http://pattern.wigner.mta.hu/participants/andras-telcs Compiled from lectures
More informationSampling-based probabilistic inference through neural and synaptic dynamics
Sampling-based probabilistic inference through neural and synaptic dynamics Wolfgang Maass for Robert Legenstein Institute for Theoretical Computer Science Graz University of Technology, Austria Institute
More informationChapter 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 informationImplementation 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 informationNeural Networks. Mark van Rossum. January 15, School of Informatics, University of Edinburgh 1 / 28
1 / 28 Neural Networks Mark van Rossum School of Informatics, University of Edinburgh January 15, 2018 2 / 28 Goals: Understand how (recurrent) networks behave Find a way to teach networks to do a certain
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 informationLecture 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 informationarxiv: v1 [q-bio.nc] 17 Jul 2017
A probabilistic model for learning in cortical microcircuit motifs with data-based divisive inhibition Robert Legenstein, Zeno Jonke, Stefan Habenschuss, Wolfgang Maass arxiv:1707.05182v1 [q-bio.nc] 17
More informationA 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 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 informationNoise as a Resource for Computation and Learning in Networks of Spiking Neurons
INVITED PAPER Noise as a Resource for Computation and Learning in Networks of Spiking Neurons This paper discusses biologically inspired machine learning methods based on theories about how the brain exploits
More informationBayesian Computation Emerges in Generic Cortical Microcircuits through Spike-Timing-Dependent Plasticity
Bayesian Computation Emerges in Generic Cortical Microcircuits through Spike-Timing-Dependent Plasticity Bernhard Nessler 1 *, Michael Pfeiffer 1,2, Lars Buesing 1, Wolfgang Maass 1 1 Institute for Theoretical
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 informationMethods for Estimating the Computational Power and Generalization Capability of Neural Microcircuits
Methods for Estimating the Computational Power and Generalization Capability of Neural Microcircuits Wolfgang Maass, Robert Legenstein, Nils Bertschinger Institute for Theoretical Computer Science Technische
More informationIntroduction to Neural Networks
Introduction to Neural Networks What are (Artificial) Neural Networks? Models of the brain and nervous system Highly parallel Process information much more like the brain than a serial computer Learning
More informationSTA 4273H: Statistical Machine Learning
STA 4273H: Statistical Machine Learning Russ Salakhutdinov Department of Computer Science! Department of Statistical Sciences! rsalakhu@cs.toronto.edu! h0p://www.cs.utoronto.ca/~rsalakhu/ Lecture 7 Approximate
More informationIntroduction 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 informationBias-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 informationCPSC 540: Machine Learning
CPSC 540: Machine Learning MCMC and Non-Parametric Bayes Mark Schmidt University of British Columbia Winter 2016 Admin I went through project proposals: Some of you got a message on Piazza. No news is
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 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 informationComputational Explorations in Cognitive Neuroscience Chapter 2
Computational Explorations in Cognitive Neuroscience Chapter 2 2.4 The Electrophysiology of the Neuron Some basic principles of electricity are useful for understanding the function of neurons. This is
More informationChapter 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 informationDeep 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 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 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 informationHertz, Krogh, Palmer: Introduction to the Theory of Neural Computation. Addison-Wesley Publishing Company (1991). (v ji (1 x i ) + (1 v ji )x i )
Symmetric Networks Hertz, Krogh, Palmer: Introduction to the Theory of Neural Computation. Addison-Wesley Publishing Company (1991). How can we model an associative memory? Let M = {v 1,..., v m } be a
More informationAn Introductory Course in Computational Neuroscience
An Introductory Course in Computational Neuroscience Contents Series Foreword Acknowledgments Preface 1 Preliminary Material 1.1. Introduction 1.1.1 The Cell, the Circuit, and the Brain 1.1.2 Physics of
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 informationLiquid Computing in a Simplified Model of Cortical Layer IV: Learning to Balance a Ball
Liquid Computing in a Simplified Model of Cortical Layer IV: Learning to Balance a Ball Dimitri Probst 1,3, Wolfgang Maass 2, Henry Markram 1, and Marc-Oliver Gewaltig 1 1 Blue Brain Project, École Polytechnique
More informationDeep 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 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 informationDynamical Constraints on Computing with Spike Timing in the Cortex
Appears in Advances in Neural Information Processing Systems, 15 (NIPS 00) Dynamical Constraints on Computing with Spike Timing in the Cortex Arunava Banerjee and Alexandre Pouget Department of Brain and
More informationInfinite systems of interacting chains with memory of variable length - a stochastic model for biological neural nets
Infinite systems of interacting chains with memory of variable length - a stochastic model for biological neural nets Antonio Galves Universidade de S.Paulo Fapesp Center for Neuromathematics Eurandom,
More informationSynaptic dynamics. John D. Murray. Synaptic currents. Simple model of the synaptic gating variable. First-order kinetics
Synaptic dynamics John D. Murray A dynamical model for synaptic gating variables is presented. We use this to study the saturation of synaptic gating at high firing rate. Shunting inhibition and the voltage
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 informationConsider the following spike trains from two different neurons N1 and N2:
About synchrony and oscillations So far, our discussions have assumed that we are either observing a single neuron at a, or that neurons fire independent of each other. This assumption may be correct in
More informationBayesian Computation Emerges in Generic Cortical Microcircuits through Spike-Timing-Dependent Plasticity
Bayesian Computation Emerges in Generic Cortical Microcircuits through Spike-Timing-Dependent Plasticity Bernhard Nessler 1,, Michael Pfeiffer 2,1, Lars Buesing 1, Wolfgang Maass 1 nessler@igi.tugraz.at,
More informationHopfield 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 informationThe Mixed States of Associative Memories Realize Unimodal Distribution of Dominance Durations in Multistable Perception
The Mixed States of Associative Memories Realize Unimodal Distribution of Dominance Durations in Multistable Perception Takashi Kanamaru Department of Mechanical Science and ngineering, School of Advanced
More informationSupporting Online Material for
www.sciencemag.org/cgi/content/full/319/5869/1543/dc1 Supporting Online Material for Synaptic Theory of Working Memory Gianluigi Mongillo, Omri Barak, Misha Tsodyks* *To whom correspondence should be addressed.
More informationEmergence of resonances in neural systems: the interplay between adaptive threshold and short-term synaptic plasticity
Emergence of resonances in neural systems: the interplay between adaptive threshold and short-term synaptic plasticity Jorge F. Mejias 1,2 and Joaquín J. Torres 2 1 Department of Physics and Center for
More informationCOMP9444 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 informationA gradient descent rule for spiking neurons emitting multiple spikes
A gradient descent rule for spiking neurons emitting multiple spikes Olaf Booij a, Hieu tat Nguyen a a Intelligent Sensory Information Systems, University of Amsterdam, Faculty of Science, Kruislaan 403,
More informationLearning Spatio-Temporally Encoded Pattern Transformations in Structured Spiking Neural Networks 12
Learning Spatio-Temporally Encoded Pattern Transformations in Structured Spiking Neural Networks 12 André Grüning, Brian Gardner and Ioana Sporea Department of Computer Science University of Surrey Guildford,
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 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 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 informationDoes the Wake-sleep Algorithm Produce Good Density Estimators?
Does the Wake-sleep Algorithm Produce Good Density Estimators? Brendan J. Frey, Geoffrey E. Hinton Peter Dayan Department of Computer Science Department of Brain and Cognitive Sciences University of Toronto
More informationComputational physics: Neural networks
Computational physics: Neural networks Bert Kappen, Biophysics University of Nijmegen June 8, 2010 Contents 1 Introduction 3 2 Networks of binary neurons 5 2.1 Neural information processing is noisy.............
More informationRestricted 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 informationMachine Learning Techniques for Computer Vision
Machine Learning Techniques for Computer Vision Part 2: Unsupervised Learning Microsoft Research Cambridge x 3 1 0.5 0.2 0 0.5 0.3 0 0.5 1 ECCV 2004, Prague x 2 x 1 Overview of Part 2 Mixture models EM
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 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 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 informationDensity 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 informationarxiv: v1 [cs.ne] 19 Sep 2015
An objective function for STDP arxiv:1509.05936v1 [cs.ne] 19 Sep 2015 Yoshua Bengio 1, Thomas Mesnard, Asja Fischer, Saizheng Zhang and Yuhuai Wu Montreal Institute for Learning Algorithms, University
More informationRestricted 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 informationLarge-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 information7.1 Basis for Boltzmann machine. 7. Boltzmann machines
7. Boltzmann machines this section we will become acquainted with classical Boltzmann machines which can be seen obsolete being rarely applied in neurocomputing. It is interesting, after all, because is
More informationConnections between score matching, contrastive divergence, and pseudolikelihood for continuous-valued variables. Revised submission to IEEE TNN
Connections between score matching, contrastive divergence, and pseudolikelihood for continuous-valued variables Revised submission to IEEE TNN Aapo Hyvärinen Dept of Computer Science and HIIT University
More informationSTDP Learning of Image Patches with Convolutional Spiking Neural Networks
STDP Learning of Image Patches with Convolutional Spiking Neural Networks Daniel J. Saunders, Hava T. Siegelmann, Robert Kozma College of Information and Computer Sciences University of Massachusetts Amherst
More informationCOMP 551 Applied Machine Learning Lecture 14: Neural Networks
COMP 551 Applied Machine Learning Lecture 14: Neural Networks Instructor: Ryan Lowe (ryan.lowe@mail.mcgill.ca) Slides mostly by: Class web page: www.cs.mcgill.ca/~hvanho2/comp551 Unless otherwise noted,
More informationGentle Introduction to Infinite Gaussian Mixture Modeling
Gentle Introduction to Infinite Gaussian Mixture Modeling with an application in neuroscience By Frank Wood Rasmussen, NIPS 1999 Neuroscience Application: Spike Sorting Important in neuroscience and for
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 informationCSC 2541: Bayesian Methods for Machine Learning
CSC 2541: Bayesian Methods for Machine Learning Radford M. Neal, University of Toronto, 2011 Lecture 3 More Markov Chain Monte Carlo Methods The Metropolis algorithm isn t the only way to do MCMC. We ll
More informationHopfield Neural Network and Associative Memory. Typical Myelinated Vertebrate Motoneuron (Wikipedia) Topic 3 Polymers and Neurons Lecture 5
Hopfield Neural Network and Associative Memory Typical Myelinated Vertebrate Motoneuron (Wikipedia) PHY 411-506 Computational Physics 2 1 Wednesday, March 5 1906 Nobel Prize in Physiology or Medicine.
More informationMachine Learning. Neural Networks. (slides from Domingos, Pardo, others)
Machine Learning Neural Networks (slides from Domingos, Pardo, others) Human Brain Neurons Input-Output Transformation Input Spikes Output Spike Spike (= a brief pulse) (Excitatory Post-Synaptic Potential)
More informationMachine Learning. Neural Networks. (slides from Domingos, Pardo, others)
Machine Learning Neural Networks (slides from Domingos, Pardo, others) For this week, Reading Chapter 4: Neural Networks (Mitchell, 1997) See Canvas For subsequent weeks: Scaling Learning Algorithms toward
More informationStochastic Networks Variations of the Hopfield model
4 Stochastic Networks 4. Variations of the Hopfield model In the previous chapter we showed that Hopfield networks can be used to provide solutions to combinatorial problems that can be expressed as the
More informationA Learning Theory for Reward-Modulated Spike-Timing-Dependent Plasticity with Application to Biofeedback
A Learning Theory for Reward-Modulated Spike-Timing-Dependent Plasticity with Application to Biofeedback Robert Legenstein, Dejan Pecevski, Wolfgang Maass Institute for Theoretical Computer Science Graz
More informationBidirectional Representation and Backpropagation Learning
Int'l Conf on Advances in Big Data Analytics ABDA'6 3 Bidirectional Representation and Bacpropagation Learning Olaoluwa Adigun and Bart Koso Department of Electrical Engineering Signal and Image Processing
More informationLearning 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 informationIntroduction Neural Networks - Architecture Network Training Small Example - ZIP Codes Summary. Neural Networks - I. Henrik I Christensen
Neural Networks - I Henrik I Christensen Robotics & Intelligent Machines @ GT Georgia Institute of Technology, Atlanta, GA 30332-0280 hic@cc.gatech.edu Henrik I Christensen (RIM@GT) Neural Networks 1 /
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 informationNeural networks. Chapter 19, Sections 1 5 1
Neural networks Chapter 19, Sections 1 5 Chapter 19, Sections 1 5 1 Outline Brains Neural networks Perceptrons Multilayer perceptrons Applications of neural networks Chapter 19, Sections 1 5 2 Brains 10
More informationNeurons as Monte Carlo Samplers: Bayesian Inference and Learning in Spiking Networks
Neurons as Monte Carlo Samplers: Bayesian Inference and Learning in Spiking Networks Yanping Huang University of Washington huangyp@cs.uw.edu Rajesh P.N. Rao University of Washington rao@cs.uw.edu Abstract
More informationFast and exact simulation methods applied on a broad range of neuron models
Fast and exact simulation methods applied on a broad range of neuron models Michiel D Haene michiel.dhaene@ugent.be Benjamin Schrauwen benjamin.schrauwen@ugent.be Ghent University, Electronics and Information
More informationNeural 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 informationNeural Nets and Symbolic Reasoning Hopfield Networks
Neural Nets and Symbolic Reasoning Hopfield Networks Outline The idea of pattern completion The fast dynamics of Hopfield networks Learning with Hopfield networks Emerging properties of Hopfield networks
More informationMachine Learning. Neural Networks. (slides from Domingos, Pardo, others)
Machine Learning Neural Networks (slides from Domingos, Pardo, others) For this week, Reading Chapter 4: Neural Networks (Mitchell, 1997) See Canvas For subsequent weeks: Scaling Learning Algorithms toward
More informationMachine 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 informationMultilayer Perceptron
Outline Hong Chang Institute of Computing Technology, Chinese Academy of Sciences Machine Learning Methods (Fall 2012) Outline Outline I 1 Introduction 2 Single Perceptron 3 Boolean Function Learning 4
More informationMarkov Chain Monte Carlo
1 Motivation 1.1 Bayesian Learning Markov Chain Monte Carlo Yale Chang In Bayesian learning, given data X, we make assumptions on the generative process of X by introducing hidden variables Z: p(z): prior
More informationNeural Networks for Machine Learning. Lecture 11a Hopfield Nets
Neural Networks for Machine Learning Lecture 11a Hopfield Nets Geoffrey Hinton Nitish Srivastava, Kevin Swersky Tijmen Tieleman Abdel-rahman Mohamed Hopfield Nets A Hopfield net is composed of binary threshold
More informationDeep 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 informationLecture 7 and 8: Markov Chain Monte Carlo
Lecture 7 and 8: Markov Chain Monte Carlo 4F13: Machine Learning Zoubin Ghahramani and Carl Edward Rasmussen Department of Engineering University of Cambridge http://mlg.eng.cam.ac.uk/teaching/4f13/ Ghahramani
More informationUndirected Graphical Models
Outline Hong Chang Institute of Computing Technology, Chinese Academy of Sciences Machine Learning Methods (Fall 2012) Outline Outline I 1 Introduction 2 Properties Properties 3 Generative vs. Conditional
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 informationPDF hosted at the Radboud Repository of the Radboud University Nijmegen
PDF hosted at the Radboud Repository of the Radboud University Nijmegen The following full text is a publisher's version. For additional information about this publication click this link. http://hdl.handle.net/2066/112727
More informationCMSC 421: Neural Computation. Applications of Neural Networks
CMSC 42: Neural Computation definition synonyms neural networks artificial neural networks neural modeling connectionist models parallel distributed processing AI perspective Applications of Neural Networks
More informationModel neurons!!poisson neurons!
Model neurons!!poisson neurons! Suggested reading:! Chapter 1.4 in Dayan, P. & Abbott, L., heoretical Neuroscience, MI Press, 2001.! Model neurons: Poisson neurons! Contents: Probability of a spike sequence
More informationAdvanced Machine Learning
Advanced Machine Learning Lecture 4: Deep Learning Essentials Pierre Geurts, Gilles Louppe, Louis Wehenkel 1 / 52 Outline Goal: explain and motivate the basic constructs of neural networks. From linear
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 informationHOPFIELD neural networks (HNNs) are a class of nonlinear
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS II: EXPRESS BRIEFS, VOL. 52, NO. 4, APRIL 2005 213 Stochastic Noise Process Enhancement of Hopfield Neural Networks Vladimir Pavlović, Member, IEEE, Dan Schonfeld,
More informationAlgorithmisches Lernen/Machine Learning
Algorithmisches Lernen/Machine Learning Part 1: Stefan Wermter Introduction Connectionist Learning (e.g. Neural Networks) Decision-Trees, Genetic Algorithms Part 2: Norman Hendrich Support-Vector Machines
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 informationNeed 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 informationArtificial Neural Networks Examination, March 2004
Artificial Neural Networks Examination, March 2004 Instructions There are SIXTY questions (worth up to 60 marks). The exam mark (maximum 60) will be added to the mark obtained in the laborations (maximum
More informationContrastive 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