Associative Learning.

Slides:



Advertisements
Similar presentations
© Negnevitsky, Pearson Education, Introduction Introduction Hebbian learning Hebbian learning Generalised Hebbian learning algorithm Generalised.
Advertisements

Introduction to Neural Networks Computing
Perceptron Learning Rule
Ming-Feng Yeh1 CHAPTER 13 Associative Learning. Ming-Feng Yeh2 Objectives The neural networks, trained in a supervised manner, require a target signal.
Neural Networks Chapter 9 Joost N. Kok Universiteit Leiden.
Self Organization: Competitive Learning
5/16/2015Intelligent Systems and Soft Computing1 Introduction Introduction Hebbian learning Hebbian learning Generalised Hebbian learning algorithm Generalised.
Artificial neural networks:
Unsupervised Networks Closely related to clustering Do not require target outputs for each input vector in the training data Inputs are connected to a.
4 1 Perceptron Learning Rule. 4 2 Learning Rules Learning Rules : A procedure for modifying the weights and biases of a network. Learning Rules : Supervised.
Linear Transformations
Simple Neural Nets For Pattern Classification
Slides are based on Negnevitsky, Pearson Education, Lecture 8 Artificial neural networks: Unsupervised learning n Introduction n Hebbian learning.
Introduction to Neural Networks John Paxton Montana State University Summer 2003.
1 Pertemuan 15 ADAPTIVE RESONANCE THEORY Matakuliah: H0434/Jaringan Syaraf Tiruan Tahun: 2005 Versi: 1.
Self Organization: Hebbian Learning CS/CMPE 333 – Neural Networks.
Perceptron Learning Rule
Associative Learning.
6 1 Linear Transformations. 6 2 Hopfield Network Questions.
1 Pertemuan 9 JARINGAN LEARNING VECTOR QUANTIZATION Matakuliah: H0434/Jaringan Syaraf Tiruan Tahun: 2005 Versi: 1.
Artificial Neural Networks Ch15. 2 Objectives Grossberg network is a self-organizing continuous-time competitive network.  Continuous-time recurrent.
October 7, 2010Neural Networks Lecture 10: Setting Backpropagation Parameters 1 Creating Data Representations On the other hand, sets of orthogonal vectors.
December 7, 2010Neural Networks Lecture 21: Hopfield Network Convergence 1 The Hopfield Network The nodes of a Hopfield network can be updated synchronously.
Lecture 09 Clustering-based Learning
Ming-Feng Yeh1 CHAPTER 3 An Illustrative Example.
CS532 Neural Networks Dr. Anwar Majid Mirza Lecture No. 3 Week2, January 22 nd, 2008 National University of Computer and Emerging.
Supervised Hebbian Learning
Artificial Neural Networks Dr. Abdul Basit Siddiqui Assistant Professor FURC.
Artificial Neural Network Unsupervised Learning
6 1 Linear Transformations. 6 2 Hopfield Network Questions The network output is repeatedly multiplied by the weight matrix W. What is the effect of this.
Chapter 8 Fuzzy Associative Memories Li Lin
1 Back-Propagation. 2 Objectives A generalization of the LMS algorithm, called backpropagation, can be used to train multilayer networks. Backpropagation.
7 1 Supervised Hebbian Learning. 7 2 Hebb’s Postulate “When an axon of cell A is near enough to excite a cell B and repeatedly or persistently takes part.
Chapter 5. Adaptive Resonance Theory (ART) ART1: for binary patterns; ART2: for continuous patterns Motivations: Previous methods have the following problem:
Unsupervised learning
Pencil-and-Paper Neural Networks Prof. Kevin Crisp St. Olaf College.
Ming-Feng Yeh1 CHAPTER 16 AdaptiveResonanceTheory.
Activations, attractors, and associators Jaap Murre Universiteit van Amsterdam
13 1 Associative Learning Simple Associative Network.
CHAPTER 14 Competitive Networks Ming-Feng Yeh.
Activations, attractors, and associators Jaap Murre Universiteit van Amsterdam en Universiteit Utrecht
1 Neural networks 2. 2 Introduction: Neural networks The nervous system contains 10^12 interconnected neurons.
A Self-organizing Semantic Map for Information Retrieval Xia Lin, Dagobert Soergel, Gary Marchionini presented by Yi-Ting.
Chapter 5 Unsupervised learning
Pertemuan 7 JARINGAN INSTAR DAN OUTSTAR
Widrow-Hoff Learning (LMS Algorithm).
Logarithms to an Arbitrary Base
Estimation Interval Estimates Industrial Engineering
Dr. Unnikrishnan P.C. Professor, EEE
Kohonen Self-organizing Feature Maps
Covariation Learning and Auto-Associative Memory
Outline Associative Learning: Hebbian Learning
Hopfield Network.
Associative Learning.
Competitive Networks.
Adaptive Resonance Theory
Neural Networks.
Grossberg Network.
Concept of a Function.
Competitive Networks.
Adaptive Resonance Theory
Remainder Theorem.
Artificial Neural Networks
Unsupervised Networks Closely related to clustering
Perceptron Learning Rule
An Illustrative Example.
Perceptron Learning Rule
Supervised Hebbian Learning
Perceptron Learning Rule
Presentation transcript:

Associative Learning

Simple Associative Network

Unconditioned Stimulus Banana Associator Unconditioned Stimulus Conditioned Stimulus

Unsupervised Hebb Rule Vector Form: Training Sequence:

Banana Recognition Example Initial Weights: Training Sequence: a = 1 First Iteration (sight fails): a 1 ( ) h r d l i m w p 0.5 – + × (no response) =

Example Second Iteration (sight works): Third Iteration (sight fails): 2 ( ) h r d l i m w p 1 0.5 – + × (banana) = Third Iteration (sight fails): Banana will now be detected if either sensor works.

Problems with Hebb Rule Weights can become arbitrarily large There is no mechanism for weights to decrease

Hebb Rule with Decay This keeps the weight matrix from growing without bound, which can be demonstrated by setting both ai and pj to 1:

Example: Banana Associator g = 0.1 First Iteration (sight fails): a 1 ( ) h r d l i m w p 0.5 – + × (no response) = Second Iteration (sight works): a 2 ( ) h r d l i m w p 1 0.5 – + × (banana) =

Third Iteration (sight fails): Example Third Iteration (sight fails): Hebb Rule Hebb with Decay

Problem of Hebb with Decay Associations will decay away if stimuli are not occasionally presented. If ai = 0, then If g = 0, this becomes Therefore the weight decays by 10% at each iteration where there is no stimulus.

Instar (Recognition Network)

Instar Operation The instar will be active when or 1 p q cos b – ³ = For normalized vectors, the largest inner product occurs when the angle between the weight vector and the input vector is zero -- the input vector is equal to the weight vector. The rows of a weight matrix represent patterns to be recognized.

Vector Recognition If we set b w 1 p – = the instar will only be active when q = 0. If we set b w 1 p – > the instar will be active for a range of angles. w 1 As b is increased, the more patterns there will be (over a wider range of q) which will activate the instar.

Instar Rule Hebb with Decay Modify so that learning and forgetting will only occur when the neuron is active - Instar Rule: w i j q ( ) 1 – a p g + = or Vector Form:

Graphical Representation For the case where the instar is active (ai = 1): or For the case where the instar is inactive (ai = 0):

Example

Training First Iteration (a=1):

Orange will now be detected if either set of sensors works. Further Training (orange) h a 2 ( ) r d l i m w p W – + = 3 1 × è ø ç ÷ æ ö a 3 ( ) h r d l i m w p W 2 – + = (orange) × 1 è ø ç ÷ æ ö Orange will now be detected if either set of sensors works.

Kohonen Rule Learning occurs when the neuron’s index i is a member of the set X(q). We will see in Chapter 14 that this can be used to train all neurons in a given neighborhood.

Outstar (Recall Network)

Outstar Operation Suppose we want the outstar to recall a certain pattern a* whenever the input p = 1 is presented to the network. Let Then, when p = 1 and the pattern is correctly recalled. The columns of a weight matrix represent patterns to be recalled.

Outstar Rule For the instar rule we made the weight decay term of the Hebb rule proportional to the output of the network. For the outstar rule we make the weight decay term proportional to the input of the network. If we make the decay rate g equal to the learning rate a, Vector Form:

Example - Pineapple Recall

Definitions

Iteration 1 a = 1

Convergence