Distributed Representation, Connection-Based Learning, and Memory Psychology 209 February 1, 2013.

Slides:



Advertisements
Similar presentations
Artificial Intelligence 12. Two Layer ANNs
Advertisements

Artificial Neural Networks (1)
Learning in Recurrent Networks Psychology 209 February 25, 2013.
5/16/2015Intelligent Systems and Soft Computing1 Introduction Introduction Hebbian learning Hebbian learning Generalised Hebbian learning algorithm Generalised.
Artificial neural networks:
Kostas Kontogiannis E&CE
Machine Learning: Connectionist McCulloch-Pitts Neuron Perceptrons Multilayer Networks Support Vector Machines Feedback Networks Hopfield Networks.
1 Neural networks 3. 2 Hopfield network (HN) model A Hopfield network is a form of recurrent artificial neural network invented by John Hopfield in 1982.
Searching for the NCC We can measure all sorts of neural correlates of these processes…so we can see the neural correlates of consciousness right? So what’s.
Simple Neural Nets For Pattern Classification
Brain Mechanisms of Unconscious Inference J. McClelland Symsys 100 April 22, 2010.
Correlation Matrix Memory CS/CMPE 333 – Neural Networks.
Introduction to Neural Networks John Paxton Montana State University Summer 2003.
1 Chapter 11 Neural Networks. 2 Chapter 11 Contents (1) l Biological Neurons l Artificial Neurons l Perceptrons l Multilayer Neural Networks l Backpropagation.
Un Supervised Learning & Self Organizing Maps Learning From Examples
COGNITIVE NEUROSCIENCE
September 16, 2010Neural Networks Lecture 4: Models of Neurons and Neural Networks 1 Capabilities of Threshold Neurons By choosing appropriate weights.
Visual Cognition II Object Perception. Theories of Object Recognition Template matching models Feature matching Models Recognition-by-components Configural.
November 30, 2010Neural Networks Lecture 20: Interpolative Associative Memory 1 Associative Networks Associative networks are able to store a set of patterns.
Laurent Itti: CS599 – Computational Architectures in Biological Vision, USC Lecture 7: Coding and Representation 1 Computational Architectures in.
November 24, 2009Introduction to Cognitive Science Lecture 21: Self-Organizing Maps 1 Self-Organizing Maps (Kohonen Maps) In the BPN, we used supervised.
Neural Networks. Background - Neural Networks can be : Biological - Biological models Artificial - Artificial models - Desire to produce artificial systems.
Cooperation of Complementary Learning Systems in Memory Review and Update on the Complementary Learning Systems Framework James L. McClelland Psychology.
CS623: Introduction to Computing with Neural Nets (lecture-10) Pushpak Bhattacharyya Computer Science and Engineering Department IIT Bombay.
CHAPTER 12 ADVANCED INTELLIGENT SYSTEMS © 2005 Prentice Hall, Decision Support Systems and Intelligent Systems, 7th Edition, Turban, Aronson, and Liang.
Supervised Hebbian Learning
Radial Basis Function Networks
Neural Networks. Plan Perceptron  Linear discriminant Associative memories  Hopfield networks  Chaotic networks Multilayer perceptron  Backpropagation.
Presentation on Neural Networks.. Basics Of Neural Networks Neural networks refers to a connectionist model that simulates the biophysical information.
 The most intelligent device - “Human Brain”.  The machine that revolutionized the whole world – “computer”.  Inefficiencies of the computer has lead.
Neural Networks Ellen Walker Hiram College. Connectionist Architectures Characterized by (Rich & Knight) –Large number of very simple neuron-like processing.
Artificial Neural Network Unsupervised Learning
Machine Learning Dr. Shazzad Hosain Department of EECS North South Universtiy
Artificial Neural Network Supervised Learning دكترمحسن كاهاني
Hebbian Coincidence Learning
Learning Theories with Technology Learning Theories with Technology By: Jessica Rubinstein.
Neural Networks and Fuzzy Systems Hopfield Network A feedback neural network has feedback loops from its outputs to its inputs. The presence of such loops.
1 Chapter 11 Neural Networks. 2 Chapter 11 Contents (1) l Biological Neurons l Artificial Neurons l Perceptrons l Multilayer Neural Networks l Backpropagation.
What to make of: distributed representations summation of inputs Hebbian plasticity ? Competitive nets Pattern associators Autoassociators.
Building high-level features using large-scale unsupervised learning Anh Nguyen, Bay-yuan Hsu CS290D – Data Mining (Spring 2014) University of California,
CSC321: Introduction to Neural Networks and machine Learning Lecture 16: Hopfield nets and simulated annealing Geoffrey Hinton.
Brain Mechanisms of Unconscious Inference J. McClelland Symsys 100 April 7, 2011.
Activations, attractors, and associators Jaap Murre Universiteit van Amsterdam
1 Lecture 6 Neural Network Training. 2 Neural Network Training Network training is basic to establishing the functional relationship between the inputs.
Introduction to Neural Networks Introduction to Neural Networks Applied to OCR and Speech Recognition An actual neuron A crude model of a neuron Computational.
Neural Networks Teacher: Elena Marchiori R4.47 Assistant: Kees Jong S2.22
Principled Probabilistic Inference and Interactive Activation Psych209 January 25, 2013.
The Emergent Structure of Semantic Knowledge
Activations, attractors, and associators Jaap Murre Universiteit van Amsterdam en Universiteit Utrecht
COSC 4426 AJ Boulay Julia Johnson Artificial Neural Networks: Introduction to Soft Computing (Textbook)
Chapter 6 Neural Network.
Object and face recognition
Memory: Its Nature and Organization in the Brain James L. McClelland Stanford University.
Pattern Associators, Generalization, Processing Psych /719 Feb 6, 2001.
1 Neural networks 2. 2 Introduction: Neural networks The nervous system contains 10^12 interconnected neurons.
CSC2535: Computation in Neural Networks Lecture 8: Hopfield nets Geoffrey Hinton.
Supervised Learning – Network is presented with the input and the desired output. – Uses a set of inputs for which the desired outputs results / classes.
INTRODUCTION TO NEURAL NETWORKS 2 A new sort of computer What are (everyday) computer systems good at... and not so good at? Good at..Not so good at..
Chapter 9 Knowledge. Some Questions to Consider Why is it difficult to decide if a particular object belongs to a particular category, such as “chair,”
CSC321 Lecture 18: Hopfield nets and simulated annealing
Neural Networks.
Cooperation of Complementary Learning Systems in Memory
Simple learning in connectionist networks
The Naïve Bayes (NB) Classifier
Artificial Intelligence 12. Two Layer ANNs
Simple learning in connectionist networks
CLS, Rapid Schema Consistent Learning, and Similarity-weighted Interleaved learning Psychology 209 Feb 26, 2019.
Volume 27, Issue 2, Pages (August 2000)
CSC 578 Neural Networks and Deep Learning
Presentation transcript:

Distributed Representation, Connection-Based Learning, and Memory Psychology 209 February 1, 2013

The Concept of a Distributed Representation Instead of assuming that an object (concept, etc) is represented in the mind by a single unit, we consider the possibility that it could be represented by patterns of activation over populations of units. The elements of the pattern may represent (approximately) some feature or sensible combination of features but they need not. What is crucial is that no units are dedicated to a single object; in general all units participate in the representation of many different objects. Neurons in the monkey visual cortex appear to exemplify these properties. Note that neurons in some parts of the brain are more selective than others but (in most people’s view) this is just a matter of degree.

Stimuli used by Baylis, Rolls, and Leonard (1991)

Responses of Four Neurons to Face and Non-Face Stimuli in Previous Slide

Responses to various stimuli by a neuron responding to a Tabby Cat (Tanaka et al, 1991)

Another Example Neuron

Example responses of cells to items in different categories Kiani et al, J Neurophysiol 97: 4296–4309, Category #cells

Kiani et al, J Neurophysiol 97: 4296–4309, 2007.

The Infamous ‘Jennifer Aniston’ Neuron

A ‘Halle Barry’ Neuron

A ‘Sydney Opera House’ Neuron Figures on this and previous two slides from: Quiroga, Q. et al, 2005, Nature, 435,

Computational Arguments for the use of Distributed Representations (Hinton et al, 1986) They use the units in a network more efficiently They support generalization on the basis of similarity They can support micro-inferences based on consistent relationships between participating units –E.g. units activated my male facial features would activate units associated with lower-pitched voices. Overlap increases generalization and micro-inferences; less overlap reduces it. There appears to be less overlap in the hippocampus than in other cortical areas – an issue to which we will return in a later lecture.

What is a Memory? The trace left in the memory system by an experience? A representation brought back to mind of a prior event or experience? Note that in some theories, these things are assumed to be one and the same (although there may be some decay or corruption).

Further questions Do we store separate representations of items and categories? –Experiments suggest participants are sensitive to item information and also to the category prototype. Exemplar models store traces of each item encountered. But what is an item? Do items ever repeat? Is it Exemplars all the way down?

A PDP Approach to Memory An experience is a pattern of activation over neurons in one or more brain regions. The trace left in memory is the set of adjustments to the strengths of the connections. –Each experience leaves such a trace, but the traces are not separable or distinct. –Rather, they are superimposed in the same set of connection weights. Recall involves the recreation of a pattern of activation, using a part or associate of it as a cue. Every act of recall is always an act of reconstruction, shaped by the traces of many other experiences.

The Hopfield Network A memory is a random pattern of 1’s and (effectivey) -1’s over the units in a network like the one shown here (there are no self- connections). To learn, a pattern is clamped on the units; weights are learned using the Hebb rule. A set of patterns can be stored in this way. The network is probed by setting the states of the units in an initial state, and then updating the units asynchronously (as in the cube example) until the activations stop changing, using a step function. Input is removed during settling. The result is the retrieved memory. –Noisy or incomplete patterns can be cleaned up or completed. Network itself makes decisions; “no complex external machinery is required” If many memories are stored, there is cross- talk among them. –If random vectors are used, capacity is only about.14*N, N being the number of units.

The McClelland/Rumelhart (1985) Distributed Memory Model Inspired by ‘Brain-State in a Box’ model of James Anderson, which predates the Hopfield net. Uses continuous units with activations between -1 and 1. Uses the same activation function as the iac model without a threshold. Net input is the sum of external plus internal inputs: net i = e i + i i Learning occurs according to the ‘Delta Rule’:  i = e i – i i w ij +=  i a j Short vs long-lasting changes to weights: –As a first approximation to this, weight increments are thought to decay rapidly from initial values to smaller more permanent values.

Basic properties of auto-associator models They can learn multiple ‘memories’ in the same set of weights –Recall: pattern completion –Recognition: strength of pattern activation –Facilitation of processing: how quickly and strongly settling occurs. With the Hebb Rule: –Orthogonal patterns can be stored without mutual contamination (up to n, but the memory ‘whites out’) With the Delta Rule: –Sets of non-orthogonal patterns can be learned, and some of the cross-talk can be eliminated with exposure. –However, over the entire set of patterns, the external input to each unit must be a linear combination of the activations of all of the other units.

Issues addressed by the M&R Distributed Memory Model Memory for general and specific information –Learning a prototype –Learning multiple prototypes in the same network –Learning general as well as specific information

Weights after learning from distortions of a prototype (each with a different ‘name’)

Sending Units Receiving Units Weights after learning Dog, Cat, and Bagel Patterns

Performance after training with several ‘dogs’, plus ‘Rover’ and ‘Fido’

Whittlesea (1983) Examined the effect of general and specific information on identification of letter strings after exposure to varying numbers and degrees of distortions to particular prototype strings.

Whittlesea’s Experiments Each experiment involved different numbers of distortions presented different numbers of times during training. Each test involved other distortions; W never tested the prototype but I did in some of my simulations. Performance measures are per-letter increase in identification compared to base line (E) and increase in dot product of input with activation due to learning (S).

Probability of choosing correct response modeled as:

Example stimuli Spared vs. impaired category vs. item learning in amnesia? This happens in the model if we simply assume amnesia reflects a smaller value of the learning rate parameter (Amnesia is a bit more interesting than this – see later lecture).

Limitations of Auto-Associator Models Capacity is limited –Different variants have different capacities –The sparser the patterns, the larger the number that can be learned Sets of patterns violating linear predictability constraint cannot be learned perfectly. Does not capture effects indicative of representational and behavioral sharpening –‘Strength Mirror Effect’ –Sharpening of neural representations after repetition We will return to these issues in a later lecture, after we have a procedure in hand for training connections into hidden units.