The PDP Approach to Understanding the Mind and Brain J. McClelland Cognitive Core Class Lecture March 7, 2011.

Slides:



Advertisements
Similar presentations
Approaches, Tools, and Applications Islam A. El-Shaarawy Shoubra Faculty of Eng.
Advertisements

Cognitive Systems, ICANN panel, Q1 What is machine intelligence, as beyond pattern matching, classification and prediction. What is machine intelligence,
ARCHITECTURES FOR ARTIFICIAL INTELLIGENCE SYSTEMS
Psycholinguistic what is psycholinguistic? 1-pyscholinguistic is the study of the cognitive process of language acquisition and use. 2-The scope of psycholinguistic.
Supervised Learning Recap
Does the Brain Use Symbols or Distributed Representations? James L. McClelland Department of Psychology and Center for Mind, Brain, and Computation Stanford.
Organization of Semantic Memory The study of Collins & Quillian (1969):Collins & Quillian (1969): The authors were interested in the organization of semantic.
Emergence in Cognitive Science: Semantic Cognition Jay McClelland Stanford University.
Emergence of Semantic Structure from Experience Jay McClelland Stanford University.
Chapter 14: Usability testing and field studies. Usability Testing Emphasizes the property of being usable Key Components –User Pre-Test –User Test –User.
Concepts and Categories. Functions of Concepts By dividing the world into classes of things to decrease the amount of information we need to learn, perceive,
Knowing Semantic memory.
Algorithms and Problem Solving. Learn about problem solving skills Explore the algorithmic approach for problem solving Learn about algorithm development.
Chapter Seven The Network Approach: Mind as a Web.
Physical Symbol System Hypothesis
Statistical Natural Language Processing. What is NLP?  Natural Language Processing (NLP), or Computational Linguistics, is concerned with theoretical.
Chapter 14: Usability testing and field studies
Machine Learning. Learning agent Any other agent.
General Knowledge Dr. Claudia J. Stanny EXP 4507 Memory & Cognition Spring 2009.
Development and Disintegration of Conceptual Knowledge: A Parallel-Distributed Processing Approach Jay McClelland Department of Psychology and Center for.
Perfection and bounded rationality in the study of cognition Henry Brighton.
Using Backprop to Understand Apects of Cognitive Development PDP Class Feb 8, 2010.
Representation, Development and Disintegration of Conceptual Knowledge: A Parallel-Distributed Processing Approach James L. McClelland Department of Psychology.
Emergence of Semantic Structure from Experience Jay McClelland Stanford University.
Theory of Cognitive Development
Outline What Neural Networks are and why they are desirable Historical background Applications Strengths neural networks and advantages Status N.N and.
Integrating New Findings into the Complementary Learning Systems Theory of Memory Jay McClelland, Stanford University.
The PDP Approach to Understanding the Mind and Brain Jay McClelland Stanford University January 21, 2014.
The Interactive Activation Model. Ubiquity of the Constraint Satisfaction Problem In sentence processing –I saw the grand canyon flying to New York –I.
Disintegration of Conceptual Knowledge In Semantic Dementia James L. McClelland Department of Psychology and Center for Mind, Brain, and Computation Stanford.
Awakening from the Cartesian Dream: The PDP Approach to Understanding the Mind and Brain Jay McClelland Stanford University February 7, 2013.
Models of Cognitive Processes: Historical Introduction with a Focus on Parallel Distributed Processing Models Psychology 209 Stanford University Jan 7,
Contrasting Approaches To Semantic Knowledge Representation and Inference Psychology 209 February 15, 2013.
Emergence of Semantic Knowledge from Experience Jay McClelland Stanford University.
PSY 323 – COGNITION Chapter 9: Knowledge.  Categorization ◦ Process by which things are placed into groups  Concept ◦ Mental groupings of similar objects,
The Influence of Feature Type, Feature Structure and Psycholinguistic Parameters on the Naming Performance of Semantic Dementia and Alzheimer’s Patients.
The Next Generation Science Standards: 4. Science and Engineering Practices Professor Michael Wysession Department of Earth and Planetary Sciences Washington.
Development, Disintegration, and Neural Basis of Semantic Cognition: A Parallel-Distributed Processing Approach James L. McClelland Department of Psychology.
Category Structure Psychology 355: Cognitive Psychology Instructor: John Miyamoto 05/20 /2015: Lecture 08-2 This Powerpoint presentation may contain macros.
Emergence of Semantic Structure from Experience Jay McClelland Stanford University.
Understanding Human Cognition through Experimental and Computational Methods Jay McClelland Symbolic Systems 100 Spring, 2011.
Similarity and Attribution Contrasting Approaches To Semantic Knowledge Representation and Inference Jay McClelland Stanford University.
Rapid integration of new schema- consistent information in the Complementary Learning Systems Theory Jay McClelland, Stanford University.
PDP Class Stanford University Jan 4, 2010
Semantic Cognition: A Parallel Distributed Processing Approach James L. McClelland Center for the Neural Basis of Cognition and Departments of Psychology.
Cognitive Processes PSY 334 Chapter 5 – Meaning-Based Knowledge Representation.
The PDP Approach to Understanding the Mind and Brain Jay McClelland Stanford University January 21, 2014.
Origins of Cognitive Abilities Jay McClelland Stanford University.
The Emergent Structure of Semantic Knowledge
Emergent Semantics: Meaning and Metaphor Jay McClelland Department of Psychology and Center for Mind, Brain, and Computation Stanford University.
From NARS to a Thinking Machine Pei Wang Temple University.
Semantic Knowledge: Its Nature, its Development, and its Neural Basis James L. McClelland Department of Psychology and Center for Mind, Brain, and Computation.
Development and Disintegration of Conceptual Knowledge: A Parallel-Distributed Processing Approach James L. McClelland Department of Psychology and Center.
ECE 8443 – Pattern Recognition ECE 8527 – Introduction to Machine Learning and Pattern Recognition Objectives: Bayes Rule Mutual Information Conditional.
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,”
Big data classification using neural network
Psychology 209 – Winter 2017 January 31, 2017
What is cognitive psychology?
Algorithms and Problem Solving
Some Aspects of the History of Cognitive Science
Development and Disintegration of Conceptual Knowledge: A Parallel-Distributed Processing Approach James L. McClelland Department of Psychology and Center.
James L. McClelland SS 100, May 31, 2011
Does the Brain Use Symbols or Distributed Representations?
Emergence of Semantic Structure from Experience
Emergence of Semantics from Experience
Some Aspects of the History of Cognitive Science
Toward a Great Class Project: Discussion of Stoianov & Zorzi’s Numerosity Model Psych 209 – 2019 Feb 14, 2019.
The Network Approach: Mind as a Web
Human Cognition: Is it more like a computer or a neural net?
Presentation transcript:

The PDP Approach to Understanding the Mind and Brain J. McClelland Cognitive Core Class Lecture March 7, 2011

Decartes’ Legacy Mechanistic approach to sensation and action Divine inspiration creates mind This leads to four dissociations: –Mind / Brain –Higher Cognitive Functions / Sensory-motor systems –Human / Animal –Descriptive / Mechanistic

Early Computational Models of Human Cognition ( ) The computer contributes to the overthrow of behaviorism. Computer simulation models emphasize strictly sequential operations, using flow charts. Simon announces that computers can ‘think’. Symbol processing languages are introduced allowing some success at theorem proving, problem solving, etc. Minsky and Pappert kill off Perceptrons. Cognitive psychologists distinguish between algorithm and hardware. Neisser deems physiology to be only of ‘peripheral interest’ Psychologists investigate mental processes as sequences of discrete stages.

Ubiquity of the Constraint Satisfaction Problem In sentence processing –I saw the grand canyon flying to New York –I saw the sheep grazing in the field In comprehension –Margie was sitting on the front steps when she heard the familiar jingle of the “Good Humor” truck. She remembered her birthday money and ran into the house. In reaching, grasping, typing…

Graded and variable nature of neuronal responses

Lateral Inhibition in Eye of Limulus (Horseshoe Crab)

The Interactive Activation Model

Distributed Representations in the Brain: Overlapping Patterns for Related Concepts (Kiani et al, 2007) doggoathammer dog goat hammer Many hundreds of single neurons recorded in monkey IT different photographs were presented twice each to each neuron. Hierarchical clustering based on the distributed representation of each picture: –The pattern of activation over all the neurons

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

The Rumelhart Model The Quillian Model

1.Show how learning could capture the emergence of hierarchical structure 2.Show how the model could make inferences as in the Quillian model DER’s Goals for the Model

ExperienceExperience Early Later Later Still

Start with a neutral representation on the representation units. Use backprop to adjust the representation to minimize the error.

The result is a representation similar to that of the average bird…

Use the representation to infer what this new thing can do.

Questions About the Rumelhart Model Does the model offer any advantages over other approaches? –Do distributed representations really buy us anything? –Can the mechanisms of learning and representation in the model tell us anything about Development? Effects of neuro-degeneration?

Phenomena in Development Progressive differentiation Overgeneralization of –Typical properties –Frequent names Emergent domain-specificity of representation Basic level advantage Expertise and frequency effects Conceptual reorganization

Disintegration in Semantic Dementia Loss of differentiation Overgeneralization

The Hierarchical Naïve Bayes Classifier Model (with R. Grosse and J. Glick) The world consists of things that belong to categories. Each category in turn may consist of things in several sub-categories. The features of members of each category are treated as independent –P({f i }|C j ) =  i p(f i |C j ) Knowledge of the features is acquired for the most inclusive category first. Successive layers of sub- categories emerge as evidence accumulates supporting the presence of co-occurrences violating the independence assumption. Living Things … Animals Plants Birds Fish Flowers Trees

PropertyOne-Class Model1 st class in two-class model 2 nd class in two-class model Can Grow1.0 0 Is Living1.0 0 Has Roots Has Leaves Has Branches Has Bark Has Petals Has Gills Has Scales Can Swim Can Fly Has Feathers Has Legs Has Skin Can See A One-Class and a Two-Class Naïve Bayes Classifier Model

Accounting for the network’s feature attributions with mixtures of classes at different levels of granularity Regression Beta Weight Epochs of Training Property attribution model: P(f i |item) =  k p(f i |c k ) + (1-  k )[(  j p(f i |c j ) + (1-  j )[…])

Should we replace the PDP model with the Naïve Bayes Classifier? It explains a lot of the data, and offers a succinct abstract characterization But –It only characterizes what’s learned when the data actually has hierarchical structure So it may be a useful approximate characterization in some cases, but can’t really replace the real thing.

Structure Extracted by a Structured Statistical Model

Predictions Similarity ratings (and patterns of inference) will violate the hierarchical structure Patterns of inference will vary by context

Experiments Size, predator/prey, and other properties affect similarity across birds, fish, and mammals Property inferences show clear context specificity Future experiments will examine whether inferences (even of biological properties) violate a hierarchical tree for items like weasels, pandas, and beavers

The Nature of Cognition, and the Place of PDP in Cognitive Theory? Many view human cognition as inherently –Structured –Systematic –Rule-governed In this framework, PDP models are seen as –Mere implementations of higher-level, rational, or ‘computational level’ models –… that don’t work as well as models that stipulate explicit rules or structures

The Alternative We argue instead that cognition (and the domains to which cognition is applied) is inherently –Quasi-regular –Semi-systematic –Context sensitive On this view, highly structured models: –Are Procrustian beds into which natural cognition fits uncomfortably –Won’t capture human cognitive abilities as well as models that allow a more graded and context sensitive conception of structure

Levels of Analysis Marr (1982) suggested we should analyze cognitive tasks at three levels: –Computation: what are the goals, what information is available, how could the information be used to achieve the goals; what is the best that can be done with the given information? –Algorithms and representations: How is information represented? What algorithms are used in manipulating representations? –Implementation: How are the algorithms and representations implemented in neural circuitry? PDP models often closely approximate (and can in many cases exactly match) idealized competence models (including structured probabilistic models). Which is the approximation? The PDP approach encourages computational level analysis but asks many questions about it: –How do we know what task – which computations – an organism is actually trying to carry out? –Is performance constrained by tasks the organism was trying to perform when it evolved or that it has performed habitually? Such constraints may be ‘wired into’ the processing mechanism, constraining its performance and preventing optimality for a given task. –The approach leads us to ask: How does the architecture and/or type of processing machinery constrain the problem and its solution? Perhaps performance is being optimized within such constraints? The PDP approach also blurs the distinction between the algorithmic and implementation levels –PDP models generally do not concern themselves with the minute details of neural implementation, and their performance often approximates performance that would be achieved by an explicit algorithm – thus they appear to lie between Marr’s algorithmic and implementation levels –PDP models do not deny that there are temporally extended cognitive processes, e.g. in problem solving and planning, that involve many steps and that can often be usefully characterized in terms of a sequence of discrete states (but leave open the possibility that insight and creativity short-circuit such processes). –The automatic and intuition-based nature of PDP models may, however, be very relevant even in our most advanced forms of cognition.