Learning Spatio-Temporally Encoded Pattern Transformations in Structured Spiking Neural Networks 12

Size: px
Start display at page:

Download "Learning Spatio-Temporally Encoded Pattern Transformations in Structured Spiking Neural Networks 12"

Transcription

1 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, UK 9th November $Id: multilayerspiker.txt :39:53Z ag15 $

2

3

4 1 Introduction 2 Background 3 Our Approach 4 Results 5 Summary

5 What are we doing? What are we doing? Formulate a supervised learning rule for spiking neural networks that Why worthwhile? can train spiking networks containing a hidden layer of neurons, can map arbitrary spatio-temporal input into arbitrary output spike patterns, ie multiple spike trains. Understand how spike-pattern based information processing takes place in the brain. A learning rule for spiking neural networks with technical potential. Find a rule that is to spiking networks what is backprop to rate neuron networks. Human Brain Project

6 Scientific Area Where are we scientifically? In the middle of nowhere between: computational neuroscience cognitive science artificial intelligence / machine learning

7

8 1 Introduction 2 Background 3 Our Approach 4 Results 5 Summary

9 Spiking Neurons (a) input spikes output spike u (c) output spike (b) input spikes Spiking neurons: real neurons communicate with each other via sequences of pulses spikes. 1 Dendritic tree, axon and cell body of a neuron. 2 Top: Spikes arrive from other neurons and its membrane potential rises. Bottom: incoming spikes on various dendrites elicit timed spikes responses as the output. 3 response of the membrane potential to incoming spikes. If the threshold θ is crossed, the membrane potential is reset to a low value, and a spike fired. From Andre Gruning and Sander Bohte. Spiking neural networks: Principles and challenges. In Proceedings of the 22nd European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning ESANN, Brugge, 214. Invited Contribution.

10 Spiking Neurons Spiking Information Processing The precise timing of spikes generated by neurons conveys meaningful information. Synaptic plasticity forms the basis of learning. Changes in synaptic strength depend on relative pre- and postsynaptic spike times, and third signals. Challenge: to relate such localised plasticity changes to learning on the network level.

11 Learning for Spiking NN General Learning Algorithms for Spiking NN? There is no general-purpose algorithm for spiking neural networks. Challenge: discontinuous nature of spiking events. Various supervised learning algorithms exist, each with its own limitations eg: network topology, adaptability (e.g. reservoir computing), limited spike encoding (e.g. latency, or spike vs no spike). Most focus on classification rather than more challenging tasks like mapping from one spike train to another.

12 Some Learning Algorithms for Spiking NN SpikeProp 3, ReSuMe 4, Tempotron 5, Chronotron 6, SPAN 7, Urbanczik and Senn 8, Brea et al. 9, Freimaux et al. 1,... 3 S.M. Bohte, J.N. Kok, and H. La Poutré. Spike-prop: error-backpropagation in multi-layer networks of spiking neurons. Neurocomputing, 48(1 4):17 37, 22 4 Filip Ponulak and Andrzej Kasiński. Supervised learning in spiking neural networks with ReSuMe: Sequence learning, classification and spike shifting. Neural Computation, 22:467 51, 21 5 Robert Gütig and Haim Sompolinsky. The tempotron: a neuron that learns spike timing-based decisions. Nature Neuroscience, 9(3), 26. doi: 1.138/nn Răzvan V Florian. The chronotron: A neuron that learns to fire temporally precise spike patterns. PLoS ONE, 7(8):e4233, A. Mohemmed, S. Schliebs, and N. Kasabov. SPAN: Spike pattern association neuron for learning spatio-temporal sequences. Int. J. Neural Systems, R. Urbanczik and W. Senn. A gradient learning rule for the tempotron. Neural Computation, 21:34 352, 29 9 Johanni Brea, Walter Senn, and Jean-Pascal Pfister. Matching recall and storage in sequence learning with spiking neural networks. The Journal of Neuroscience, 33(23): , Nicolas Fremaux, Henning Sprekeler, and Wulfram Gerstner. Functional requirements for reward-modulated spile-timing-dependent plasticity. The Journal of Neuroscience, 3(4): , 1 21

13

14 1 Introduction 2 Background 3 Our Approach 4 Results 5 Summary

15 Our Approach MultilayerSpiker Generalise backpropagation to Spiking Neural Networks with hidden neurons. Use stochastic neuron model to connect smooth quantities (derivative exists) with discrete spike trains (no derivative)

16 Neuron model Membrane potential u o (t) := h w oh t t Y h (t )ɛ(t t )dt + Z o (t )κ(t t )dt, (1) o postsynaptic neurons, h presynaptic neuron u o membrane potential of o. w oh strength of synaptic connection from h to o. Y h (t) = t h <t δ(t t h) spike train of neuron h where t h are the firing times of h Z o (t) = t o<t δ(t t o) spike train of neuron o where t o are the firing times of o.

17 Neuron model Spike response kernel ɛ and reset kernel κ ɛ(s) = ɛ [e s/τm e s/τs ] Θ(s) and κ(s) = κ e s/τm Θ(s), (2) spike response kernel ɛ = 4mV, reset kernel κ = 15mV, membrane time constant τ m = 1ms, the synaptic rise time τ s = 5ms Heaviside step function Θ(s).

18 Neuron model Stochastic Intensity (instantaneous firing rate) and Spikes ( ) u(t) ϑ ρ(t) = ρ[u(t)] = ρ exp, (3) u firing rate at threshold ρ =.1ms 1. threshold ϑ = 15mV. smoothness of the threshold u o =.2mV (output layer) or u h = 2mV (hidden layer) Spikes are generated by a point process taking stochastic intensity ρ o (t). Ie in a small time interval [t, t + δt) a spike is generated with probability ρ o (t)δt.

19 Backpropagation Objective ( Error ) function ( ) P(zo ref x) = exp log (ρ o (t)) Zo ref (t) ρ o (t)dt, (4) where Zo ref (t) = f δ(t t o f ) is the target output spike train for input x. a a J. P. Pfister, T. Toyoizumi, K. Aihara, and W. Gerstner. Optimal spike-timing dependent plasticity for precise action potential firing in supervised learning. Neural Computation, 18(6): , 26 Backprop approach w oh = η o log P(z ref x) w oh (5)

20 Backprop approach... and some ten slides later Lots of derivatives, indices, probabilities. Derivatives only possible due to smoothness of probability function. Relatively freely switching between expected values and their best estimates to be had when you only have single cast.

21 Backprop Weight Update Backpropagated Error Signal δ o (t) := 1 [ u o Hidden-to-Output Weights Input-to-Hidden Weights a Zo ref ] (t) ρ o (t), (6) T w oh = η o δ o (t) (Y h ɛ)(t) dt. (7) w hi = η T h w oh δ o (t)([y h (X i ɛ)] ɛ)(t)dt. (8) u h o a Brian Gardner, Ioana Sporea, and Andre Gruning. Learning spatio-temporally encoded pattern transformations in structured spiking neural networks. Neural Computation, To appear Preprint available at

22

23 1 Introduction 2 Background 3 Our Approach 4 Results 5 Summary

24 Task Task Purpose: explore the properties of the new learning algorithm. Map an input (given as a set of spike trains) to an output (given again as a set of spike trains). Simulation details a. a Brian Gardner, Ioana Sporea, and Andre Gruning. Learning spatio-temporally encoded pattern transformations in structured spiking neural networks. Neural Computation, To appear Preprint available at

25 Introduction Background Our Approach Results Network Setup Input spike pattern 1 Input A Xi Hidden D Hidden neuron B Episodes Output 4 2 Output neuron E Time (ms) 4 5 Distance C Episodes Episodes 8 1 Left: spike rasters of input, hidden and output layers (with targets). Right top: network structure, bottom: van-rossum distance. Summary

26 Network in Action X i u h ϑ u o ϑ T (X i ǫ) T ([Y h (X i ǫ)] ǫ) T w hi Left: Input spike train X i (top) and its evoked post synaptic potential X i ɛ (bottom). Middle: Fluctuations of a hidden neuron membrane potential u h relative to a firing threshold ϑ, in response to inputs from input layer (top). The potential dependent factor of the back propagated error from hidden to input layer [Y h (X i ɛ)] bottom left: corresponding PSP (according to kernel X i ɛ). Right: membrane potential of an output neuron u o, in response to hidden layer activity. Target indicated by dotted lines (top). Weight changes of input-to-hidden weight due to learning rule.

27 Experiments Performance (%) Input patterns Episodes Free w hi Fixed w hi Single layer Input patterns Dependence of the performance on the number of input patterns and network setup. Each input pattern mapped to a unique target output of single output neuron and spike. Left: performance as a function of the number of input patterns. Right: Number of episodes to convergence in learning. Blue curves: hidden weights w hi updated according to learning algorithm, red curves: fixed random weights (plus homoeostasis), green: single layer.

28 Experiments A Performance (%) n o = 1 n o = 2 n o = n h / n o B n h / n o n o = Number of output spikes Dependence of the performance on the ratio of hidden to output neurons, and the number of target output spikes. p = 5. A unique target output spike pattern for each output neuron. (Left) Performance as a function of the ratio of hidden to output neurons. (Right) Minimum ratio of hidden to output neurons required to achieve 9% performance.

29

30 1 Introduction 2 Background 3 Our Approach 4 Results 5 Summary

31 Summary Results Compared to other learning algorithms for spiking neuron networks, we can learn more input-output mappings: 2 classes or 2 individual patterns here vs 3-4 more timed output spikes: up to 1 individually timed spikes here vs 3-5 with multiple outputs: up to 3 here vs 1 Apply it! MultilayerSpiker opens up the use of spiking neural networks for technical/cognitive modelling tasks. Spiking networks are biologically plausible. Explore how computations can be done with neural networks. Next step in the Human Brain Project: Implementation on SpiNNaker, and other neural hardware.

32 Spiking Neural Networks Open Questions How do networks of spiking neurons carry out computations? How can they learn such computations? Does this explain how real biological neurons compute? What is the applied killer application?

A gradient descent rule for spiking neurons emitting multiple spikes

A 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 information

SuperSpike: Supervised learning in multi-layer spiking neural networks

SuperSpike: Supervised learning in multi-layer spiking neural networks SuperSpike: Supervised learning in multi-layer spiking neural networks arxiv:1705.11146v2 [q-bio.nc] 14 Oct 2017 Friedemann Zenke 1, 2 & Surya Ganguli 1 1 Department of Applied Physics Stanford University

More information

arxiv: v1 [cs.lg] 9 Dec 2016

arxiv: v1 [cs.lg] 9 Dec 2016 Towards deep learning with spiking neurons in energy based models with contrastive Hebbian plasticity arxiv:1612.03214v1 [cs.lg] 9 Dec 2016 Thomas Mesnard École Normale Supérieure Paris, France thomas.mesnard@ens.fr

More information

CSE/NB 528 Final Lecture: All Good Things Must. CSE/NB 528: Final Lecture

CSE/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 information

arxiv: v1 [cs.ne] 23 Oct 2018

arxiv: v1 [cs.ne] 23 Oct 2018 TRAINING MULTILAYER SPIKING NEURAL NETWORKS USING NORMAD BASED SPATIO-TEMPORAL ERROR BACKPROPAGATION A PREPRINT arxiv:1811.10678v1 [cs.ne] 23 Oct 2018 Navin Anwani Department of Electrical Engineering

More information

Event-Driven Random Backpropagation: Enabling Neuromorphic Deep Learning Machines

Event-Driven Random Backpropagation: Enabling Neuromorphic Deep Learning Machines Event-Driven Random Backpropagation: Enabling Neuromorphic Deep Learning Machines Emre Neftci Department of Cognitive Sciences, UC Irvine, Department of Computer Science, UC Irvine, March 7, 2017 Scalable

More information

(Feed-Forward) Neural Networks Dr. Hajira Jabeen, Prof. Jens Lehmann

(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 information

Data Mining Part 5. Prediction

Data Mining Part 5. Prediction Data Mining Part 5. Prediction 5.5. Spring 2010 Instructor: Dr. Masoud Yaghini Outline How the Brain Works Artificial Neural Networks Simple Computing Elements Feed-Forward Networks Perceptrons (Single-layer,

More information

Neuronal Dynamics: Computational Neuroscience of Single Neurons

Neuronal Dynamics: Computational Neuroscience of Single Neurons Week 5 part 3a :Three definitions of rate code Neuronal Dynamics: Computational Neuroscience of Single Neurons Week 5 Variability and Noise: The question of the neural code Wulfram Gerstner EPFL, Lausanne,

More information

Temporal Pattern Analysis

Temporal Pattern Analysis LIACS Leiden Institute of Advanced Computer Science Master s Thesis June 17, 29 Temporal Pattern Analysis Using Reservoir Computing Author: Ron Vink Supervisor: Dr. Walter Kosters 1 Contents 1 Introduction

More information

Probabilistic Models in Theoretical Neuroscience

Probabilistic 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 information

Modelling stochastic neural learning

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 information

STDP Learning of Image Patches with Convolutional Spiking Neural Networks

STDP 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 information

Deep learning in the brain. Deep learning summer school Montreal 2017

Deep learning in the brain. Deep learning summer school Montreal 2017 Deep learning in the brain Deep learning summer school Montreal 207 . Why deep learning is not just for AI The recent success of deep learning in artificial intelligence (AI) means that most people associate

More information

Neural Networks. Nicholas Ruozzi University of Texas at Dallas

Neural Networks. Nicholas Ruozzi University of Texas at Dallas Neural Networks Nicholas Ruozzi University of Texas at Dallas Handwritten Digit Recognition Given a collection of handwritten digits and their corresponding labels, we d like to be able to correctly classify

More information

Spiking Neural Network Training Using Evolutionary Algorithms

Spiking Neural Network Training Using Evolutionary Algorithms Spiking Neural Network Training Using Evolutionary Algorithms N.G. Pavlidis 1,2, D.K. Tasoulis 1,2,V.P.Plagianakos 1,2, G. Nikiforidis 3,4 and M.N. Vrahatis 1,2 1 Department of Mathematics, University

More information

Fast classification using sparsely active spiking networks. Hesham Mostafa Institute of neural computation, UCSD

Fast classification using sparsely active spiking networks. Hesham Mostafa Institute of neural computation, UCSD Fast classification using sparsely active spiking networks Hesham Mostafa Institute of neural computation, UCSD Artificial networks vs. spiking networks backpropagation output layer Multi-layer networks

More information

A 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 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 information

Learning Beyond Finite Memory in Recurrent Networks Of Spiking Neurons

Learning Beyond Finite Memory in Recurrent Networks Of Spiking Neurons Learning Beyond Finite Memory in Recurrent Networks Of Spiking Neurons Peter Tiňo 1 Ashley Mills 1 School Of Computer Science, University Of Birmingham, Birmingham B15 2TT, UK P.Tino@cs.bham.ac.uk, msc57ajm@cs.bham.ac.uk

More information

Machine Learning. Neural Networks. (slides from Domingos, Pardo, others)

Machine 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 information

Hopfield 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) 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 information

Introduction to Neural Networks

Introduction 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 information

COGS Q250 Fall Homework 7: Learning in Neural Networks Due: 9:00am, Friday 2nd November.

COGS Q250 Fall Homework 7: Learning in Neural Networks Due: 9:00am, Friday 2nd November. COGS Q250 Fall 2012 Homework 7: Learning in Neural Networks Due: 9:00am, Friday 2nd November. For the first two questions of the homework you will need to understand the learning algorithm using the delta

More information

This script will produce a series of pulses of amplitude 40 na, duration 1ms, recurring every 50 ms.

This script will produce a series of pulses of amplitude 40 na, duration 1ms, recurring every 50 ms. 9.16 Problem Set #4 In the final problem set you will combine the pieces of knowledge gained in the previous assignments to build a full-blown model of a plastic synapse. You will investigate the effects

More information

AN INTRODUCTION TO NEURAL NETWORKS. Scott Kuindersma November 12, 2009

AN INTRODUCTION TO NEURAL NETWORKS. Scott Kuindersma November 12, 2009 AN INTRODUCTION TO NEURAL NETWORKS Scott Kuindersma November 12, 2009 SUPERVISED LEARNING We are given some training data: We must learn a function If y is discrete, we call it classification If it is

More information

Evolution of the Average Synaptic Update Rule

Evolution of the Average Synaptic Update Rule Supporting Text Evolution of the Average Synaptic Update Rule In this appendix we evaluate the derivative of Eq. 9 in the main text, i.e., we need to calculate log P (yk Y k, X k ) γ log P (yk Y k ). ()

More information

Fast neural network simulations with population density methods

Fast neural network simulations with population density methods Fast neural network simulations with population density methods Duane Q. Nykamp a,1 Daniel Tranchina b,a,c,2 a Courant Institute of Mathematical Science b Department of Biology c Center for Neural Science

More information

On the Complexity of Acyclic Networks of Neurons

On the Complexity of Acyclic Networks of Neurons On the Complexity of Acyclic Networks of Neurons Venkatakrishnan Ramaswamy CISE University of Florida vr1@cise.ufl.edu Arunava Banerjee CISE University of Florida arunava@cise.ufl.edu September 8, 2009

More information

Neural Networks. Chapter 18, Section 7. TB Artificial Intelligence. Slides from AIMA 1/ 21

Neural Networks. Chapter 18, Section 7. TB Artificial Intelligence. Slides from AIMA   1/ 21 Neural Networks Chapter 8, Section 7 TB Artificial Intelligence Slides from AIMA http://aima.cs.berkeley.edu / 2 Outline Brains Neural networks Perceptrons Multilayer perceptrons Applications of neural

More information

Reducing the Variability of Neural Responses: A Computational Theory of Spike-Timing-Dependent Plasticity

Reducing the Variability of Neural Responses: A Computational Theory of Spike-Timing-Dependent Plasticity LETTER Communicated by Gal Chechik Reducing the Variability of Neural Responses: A Computational Theory of Spike-Timing-Dependent Plasticity Sander M. Bohte sbohte@cwi.nl Netherlands Centre for Mathematics

More information

Spiking neural network-based control chart pattern recognition

Spiking neural network-based control chart pattern recognition Alexandria Engineering Journal (2012) 51, 27 35 Alexandria University Alexandria Engineering Journal www.elsevier.com/locate/ae www.sciencedirect.com Spiking neural network-based control chart pattern

More information

Neural Networks. Mark van Rossum. January 15, School of Informatics, University of Edinburgh 1 / 28

Neural 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 information

Synaptic dynamics. John D. Murray. Synaptic currents. Simple model of the synaptic gating variable. First-order kinetics

Synaptic 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 information

The Spike Response Model: A Framework to Predict Neuronal Spike Trains

The Spike Response Model: A Framework to Predict Neuronal Spike Trains The Spike Response Model: A Framework to Predict Neuronal Spike Trains Renaud Jolivet, Timothy J. Lewis 2, and Wulfram Gerstner Laboratory of Computational Neuroscience, Swiss Federal Institute of Technology

More information

ARTIFICIAL NEURAL NETWORK PART I HANIEH BORHANAZAD

ARTIFICIAL NEURAL NETWORK PART I HANIEH BORHANAZAD ARTIFICIAL NEURAL NETWORK PART I HANIEH BORHANAZAD WHAT IS A NEURAL NETWORK? The simplest definition of a neural network, more properly referred to as an 'artificial' neural network (ANN), is provided

More information

ARTIFICIAL INTELLIGENCE. Artificial Neural Networks

ARTIFICIAL INTELLIGENCE. Artificial Neural Networks INFOB2KI 2017-2018 Utrecht University The Netherlands ARTIFICIAL INTELLIGENCE Artificial Neural Networks Lecturer: Silja Renooij These slides are part of the INFOB2KI Course Notes available from www.cs.uu.nl/docs/vakken/b2ki/schema.html

More information

Machine Learning. Neural Networks. (slides from Domingos, Pardo, others)

Machine 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 information

Artifical Neural Networks

Artifical Neural Networks Neural Networks Artifical Neural Networks Neural Networks Biological Neural Networks.................................. Artificial Neural Networks................................... 3 ANN Structure...........................................

More information

Machine Learning. Neural Networks. (slides from Domingos, Pardo, others)

Machine 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 information

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

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

More information

Artificial Neural Network

Artificial Neural Network Artificial Neural Network Contents 2 What is ANN? Biological Neuron Structure of Neuron Types of Neuron Models of Neuron Analogy with human NN Perceptron OCR Multilayer Neural Network Back propagation

More information

2015 Todd Neller. A.I.M.A. text figures 1995 Prentice Hall. Used by permission. Neural Networks. Todd W. Neller

2015 Todd Neller. A.I.M.A. text figures 1995 Prentice Hall. Used by permission. Neural Networks. Todd W. Neller 2015 Todd Neller. A.I.M.A. text figures 1995 Prentice Hall. Used by permission. Neural Networks Todd W. Neller Machine Learning Learning is such an important part of what we consider "intelligence" that

More information

How to do backpropagation in a brain

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

More information

Liquid 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 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 information

Artificial Neural Networks. Q550: Models in Cognitive Science Lecture 5

Artificial Neural Networks. Q550: Models in Cognitive Science Lecture 5 Artificial Neural Networks Q550: Models in Cognitive Science Lecture 5 "Intelligence is 10 million rules." --Doug Lenat The human brain has about 100 billion neurons. With an estimated average of one thousand

More information

Computational Explorations in Cognitive Neuroscience Chapter 2

Computational 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 information

Reducing Spike Train Variability: A Computational Theory Of Spike-Timing Dependent Plasticity

Reducing Spike Train Variability: A Computational Theory Of Spike-Timing Dependent Plasticity Reducing Spike Train Variability: A Computational Theory Of Spike-Timing Dependent Plasticity Sander M. Bohte a Michael C. Mozer b a CWI, Kruislaan 413, 1098 SJ Amsterdam, The Netherlands b Dept. of Computer

More information

Math in systems neuroscience. Quan Wen

Math in systems neuroscience. Quan Wen Math in systems neuroscience Quan Wen Human brain is perhaps the most complex subject in the universe 1 kg brain 10 11 neurons 180,000 km nerve fiber 10 15 synapses 10 18 synaptic proteins Multiscale

More information

Artificial Neural Networks. Historical description

Artificial 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 information

Biological Modeling of Neural Networks:

Biological Modeling of Neural Networks: Week 14 Dynamics and Plasticity 14.1 Reservoir computing - Review:Random Networks - Computing with rich dynamics Biological Modeling of Neural Networks: 14.2 Random Networks - stationary state - chaos

More information

Feedforward Neural Nets and Backpropagation

Feedforward Neural Nets and Backpropagation Feedforward Neural Nets and Backpropagation Julie Nutini University of British Columbia MLRG September 28 th, 2016 1 / 23 Supervised Learning Roadmap Supervised Learning: Assume that we are given the features

More information

Dynamical Constraints on Computing with Spike Timing in the Cortex

Dynamical 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 information

AI Programming CS F-20 Neural Networks

AI Programming CS F-20 Neural Networks AI Programming CS662-2008F-20 Neural Networks David Galles Department of Computer Science University of San Francisco 20-0: Symbolic AI Most of this class has been focused on Symbolic AI Focus or symbols

More information

Sampling-based probabilistic inference through neural and synaptic dynamics

Sampling-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 information

Linear Regression, Neural Networks, etc.

Linear Regression, Neural Networks, etc. Linear Regression, Neural Networks, etc. Gradient Descent Many machine learning problems can be cast as optimization problems Define a function that corresponds to learning error. (More on this later)

More information

Supporting Online Material for

Supporting 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 information

Synaptic Devices and Neuron Circuits for Neuron-Inspired NanoElectronics

Synaptic Devices and Neuron Circuits for Neuron-Inspired NanoElectronics Synaptic Devices and Neuron Circuits for Neuron-Inspired NanoElectronics Byung-Gook Park Inter-university Semiconductor Research Center & Department of Electrical and Computer Engineering Seoul National

More information

What Can a Neuron Learn with Spike-Timing-Dependent Plasticity?

What Can a Neuron Learn with Spike-Timing-Dependent Plasticity? LETTER Communicated by Wulfram Gerstner What Can a Neuron Learn with Spike-Timing-Dependent Plasticity? Robert Legenstein legi@igi.tugraz.at Christian Naeger naeger@gmx.de Wolfgang Maass maass@igi.tugraz.at

More information

COMP 551 Applied Machine Learning Lecture 14: Neural Networks

COMP 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 information

Lecture 10. Neural networks and optimization. Machine Learning and Data Mining November Nando de Freitas UBC. Nonlinear Supervised Learning

Lecture 10. Neural networks and optimization. Machine Learning and Data Mining November Nando de Freitas UBC. Nonlinear Supervised Learning Lecture 0 Neural networks and optimization Machine Learning and Data Mining November 2009 UBC Gradient Searching for a good solution can be interpreted as looking for a minimum of some error (loss) function

More information

Simple neuron model Components of simple neuron

Simple neuron model Components of simple neuron Outline 1. Simple neuron model 2. Components of artificial neural networks 3. Common activation functions 4. MATLAB representation of neural network. Single neuron model Simple neuron model Components

More information

Information Theory and Neuroscience II

Information Theory and Neuroscience II John Z. Sun and Da Wang Massachusetts Institute of Technology October 14, 2009 Outline System Model & Problem Formulation Information Rate Analysis Recap 2 / 23 Neurons Neuron (denoted by j) I/O: via synapses

More information

Neural Networks. Xiaojin Zhu Computer Sciences Department University of Wisconsin, Madison. slide 1

Neural Networks. Xiaojin Zhu Computer Sciences Department University of Wisconsin, Madison. slide 1 Neural Networks Xiaoin Zhu erryzhu@cs.wisc.edu Computer Sciences Department University of Wisconsin, Madison slide 1 Terminator 2 (1991) JOHN: Can you learn? So you can be... you know. More human. Not

More information

arxiv: v2 [cs.ne] 16 Aug 2017

arxiv: v2 [cs.ne] 16 Aug 2017 Supervised learning based on temporal coding in spiking neural networks arxiv:1606.08165v2 [cs.ne] 16 Aug 2017 Hesham Mostafa Department of Bioengineering, Jacobs School of Engineering Institute of Neural

More information

EEE 241: Linear Systems

EEE 241: Linear Systems EEE 4: Linear Systems Summary # 3: Introduction to artificial neural networks DISTRIBUTED REPRESENTATION An ANN consists of simple processing units communicating with each other. The basic elements of

More information

Learning and Memory in Neural Networks

Learning 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 information

Artificial Neural Network and Fuzzy Logic

Artificial 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 information

Neural Networks: Introduction

Neural Networks: Introduction Neural Networks: Introduction Machine Learning Fall 2017 Based on slides and material from Geoffrey Hinton, Richard Socher, Dan Roth, Yoav Goldberg, Shai Shalev-Shwartz and Shai Ben-David, and others 1

More information

Triplets of Spikes in a Model of Spike Timing-Dependent Plasticity

Triplets of Spikes in a Model of Spike Timing-Dependent Plasticity The Journal of Neuroscience, September 20, 2006 26(38):9673 9682 9673 Behavioral/Systems/Cognitive Triplets of Spikes in a Model of Spike Timing-Dependent Plasticity Jean-Pascal Pfister and Wulfram Gerstner

More information

Methods for Estimating the Computational Power and Generalization Capability of Neural Microcircuits

Methods 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 information

Spike-based Long Short-Term Memory networks

Spike-based Long Short-Term Memory networks Spike-based Long Short-Term Memory networks MSc Thesis Roeland Nusselder Mathematical Institute Utrecht University Machine Learning CWI Amsterdam Project supervisor: Prof. dr. R.H. Bisseling Daily supervisors:

More information

Lecture 7 Artificial neural networks: Supervised learning

Lecture 7 Artificial neural networks: Supervised learning Lecture 7 Artificial neural networks: Supervised learning Introduction, or how the brain works The neuron as a simple computing element The perceptron Multilayer neural networks Accelerated learning in

More information

4. Multilayer Perceptrons

4. Multilayer Perceptrons 4. Multilayer Perceptrons This is a supervised error-correction learning algorithm. 1 4.1 Introduction A multilayer feedforward network consists of an input layer, one or more hidden layers, and an output

More information

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

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

More information

Neural networks. Chapter 20, Section 5 1

Neural 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

Neural Networks. Bishop PRML Ch. 5. Alireza Ghane. Feed-forward Networks Network Training Error Backpropagation Applications

Neural Networks. Bishop PRML Ch. 5. Alireza Ghane. Feed-forward Networks Network Training Error Backpropagation Applications Neural Networks Bishop PRML Ch. 5 Alireza Ghane Neural Networks Alireza Ghane / Greg Mori 1 Neural Networks Neural networks arise from attempts to model human/animal brains Many models, many claims of

More information

Novel VLSI Implementation for Triplet-based Spike-Timing Dependent Plasticity

Novel VLSI Implementation for Triplet-based Spike-Timing Dependent Plasticity Novel LSI Implementation for Triplet-based Spike-Timing Dependent Plasticity Mostafa Rahimi Azghadi, Omid Kavehei, Said Al-Sarawi, Nicolangelo Iannella, and Derek Abbott Centre for Biomedical Engineering,

More information

Neuron. Detector Model. Understanding Neural Components in Detector Model. Detector vs. Computer. Detector. Neuron. output. axon

Neuron. Detector Model. Understanding Neural Components in Detector Model. Detector vs. Computer. Detector. Neuron. output. axon Neuron Detector Model 1 The detector model. 2 Biological properties of the neuron. 3 The computational unit. Each neuron is detecting some set of conditions (e.g., smoke detector). Representation is what

More information

Lecture 6. Notes on Linear Algebra. Perceptron

Lecture 6. Notes on Linear Algebra. Perceptron Lecture 6. Notes on Linear Algebra. Perceptron COMP90051 Statistical Machine Learning Semester 2, 2017 Lecturer: Andrey Kan Copyright: University of Melbourne This lecture Notes on linear algebra Vectors

More information

CISC 3250 Systems Neuroscience

CISC 3250 Systems Neuroscience CISC 3250 Systems Neuroscience Systems Neuroscience How the nervous system performs computations How groups of neurons work together to achieve intelligence Professor Daniel Leeds dleeds@fordham.edu JMH

More information

On the Computational Complexity of Networks of Spiking Neurons

On the Computational Complexity of Networks of Spiking Neurons On the Computational Complexity of Networks of Spiking Neurons (Extended Abstract) Wolfgang Maass Institute for Theoretical Computer Science Technische Universitaet Graz A-80lO Graz, Austria e-mail: maass@igi.tu-graz.ac.at

More information

Biosciences in the 21st century

Biosciences in the 21st century Biosciences in the 21st century Lecture 1: Neurons, Synapses, and Signaling Dr. Michael Burger Outline: 1. Why neuroscience? 2. The neuron 3. Action potentials 4. Synapses 5. Organization of the nervous

More information

Artificial Neural Networks

Artificial Neural Networks Artificial Neural Networks 鮑興國 Ph.D. National Taiwan University of Science and Technology Outline Perceptrons Gradient descent Multi-layer networks Backpropagation Hidden layer representations Examples

More information

Introduction to Natural Computation. Lecture 9. Multilayer Perceptrons and Backpropagation. Peter Lewis

Introduction to Natural Computation. Lecture 9. Multilayer Perceptrons and Backpropagation. Peter Lewis Introduction to Natural Computation Lecture 9 Multilayer Perceptrons and Backpropagation Peter Lewis 1 / 25 Overview of the Lecture Why multilayer perceptrons? Some applications of multilayer perceptrons.

More information

Lecture 11 : Simple Neuron Models. Dr Eileen Nugent

Lecture 11 : Simple Neuron Models. Dr Eileen Nugent Lecture 11 : Simple Neuron Models Dr Eileen Nugent Reading List Nelson, Biological Physics, Chapter 12 Phillips, PBoC, Chapter 17 Gerstner, Neuronal Dynamics: from single neurons to networks and models

More information

Artificial Neural Networks The Introduction

Artificial Neural Networks The Introduction Artificial Neural Networks The Introduction 01001110 01100101 01110101 01110010 01101111 01101110 01101111 01110110 01100001 00100000 01110011 01101011 01110101 01110000 01101001 01101110 01100001 00100000

More information

Lecture 4: Perceptrons and Multilayer Perceptrons

Lecture 4: Perceptrons and Multilayer Perceptrons Lecture 4: Perceptrons and Multilayer Perceptrons Cognitive Systems II - Machine Learning SS 2005 Part I: Basic Approaches of Concept Learning Perceptrons, Artificial Neuronal Networks Lecture 4: Perceptrons

More information

How do biological neurons learn? Insights from computational modelling of

How do biological neurons learn? Insights from computational modelling of How do biological neurons learn? Insights from computational modelling of neurobiological experiments Lubica Benuskova Department of Computer Science University of Otago, New Zealand Brain is comprised

More information

Processing of temporal structured information by spiking neural networks

Processing of temporal structured information by spiking neural networks Processing of temporal structured information by spiking neural networks A dissertation presented by Cătălin V. Rusu under supervision of prof. Leon Ţâmbulea summary Submitted to the Babeş-Bolyai University

More information

The 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 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 information

Course 395: Machine Learning - Lectures

Course 395: Machine Learning - Lectures Course 395: Machine Learning - Lectures Lecture 1-2: Concept Learning (M. Pantic) Lecture 3-4: Decision Trees & CBC Intro (M. Pantic & S. Petridis) Lecture 5-6: Evaluating Hypotheses (S. Petridis) Lecture

More information

Last update: October 26, Neural networks. CMSC 421: Section Dana Nau

Last update: October 26, Neural networks. CMSC 421: Section Dana Nau Last update: October 26, 207 Neural networks CMSC 42: Section 8.7 Dana Nau Outline Applications of neural networks Brains Neural network units Perceptrons Multilayer perceptrons 2 Example Applications

More information

Emergence 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 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 information

Artificial Neural Networks" and Nonparametric Methods" CMPSCI 383 Nov 17, 2011!

Artificial Neural Networks and Nonparametric Methods CMPSCI 383 Nov 17, 2011! Artificial Neural Networks" and Nonparametric Methods" CMPSCI 383 Nov 17, 2011! 1 Todayʼs lecture" How the brain works (!)! Artificial neural networks! Perceptrons! Multilayer feed-forward networks! Error

More information

Apprentissage, réseaux de neurones et modèles graphiques (RCP209) Neural Networks and Deep Learning

Apprentissage, réseaux de neurones et modèles graphiques (RCP209) Neural Networks and Deep Learning Apprentissage, réseaux de neurones et modèles graphiques (RCP209) Neural Networks and Deep Learning Nicolas Thome Prenom.Nom@cnam.fr http://cedric.cnam.fr/vertigo/cours/ml2/ Département Informatique Conservatoire

More information

Machine Learning. Neural Networks

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

More information

Neural networks. Chapter 19, Sections 1 5 1

Neural 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 information

Back-propagation as reinforcement in prediction tasks

Back-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 information

Machine Learning I Continuous Reinforcement Learning

Machine Learning I Continuous Reinforcement Learning Machine Learning I Continuous Reinforcement Learning Thomas Rückstieß Technische Universität München January 7/8, 2010 RL Problem Statement (reminder) state s t+1 ENVIRONMENT reward r t+1 new step r t

More information

Emergence of network structure due to spike-timing-dependent plasticity in recurrent neuronal networks IV

Emergence of network structure due to spike-timing-dependent plasticity in recurrent neuronal networks IV Biol Cybern (2009) 101:427 444 DOI 10.1007/s00422-009-0346-1 ORIGINAL PAPER Emergence of network structure due to spike-timing-dependent plasticity in recurrent neuronal networks IV Structuring synaptic

More information