Contrasting Approaches To Semantic Knowledge Representation and Inference Psychology 209 February 15, 2013.

Slides:



Advertisements
Similar presentations
Pat Langley Computational Learning Laboratory Center for the Study of Language and Information Stanford University, Stanford, California USA
Advertisements

Artificial Intelligence 12. Two Layer ANNs
Naïve-Bayes Classifiers Business Intelligence for Managers.
Machine Learning in Practice Lecture 7 Carolyn Penstein Rosé Language Technologies Institute/ Human-Computer Interaction Institute.
Learning in Recurrent Networks Psychology 209 February 25, 2013.
PDP: Motivation, basic approach. Cognitive psychology or “How the Mind Works”
Does the Brain Use Symbols or Distributed Representations? James L. McClelland Department of Psychology and Center for Mind, Brain, and Computation Stanford.
Knowledge ß How do we organize our knowledge? ß How do we access our knowledge? ß Do we really use categories?
Emergence in Cognitive Science: Semantic Cognition Jay McClelland Stanford University.
Emergence of Semantic Structure from Experience Jay McClelland Stanford University.
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.
COGNITIVE NEUROSCIENCE
Physical Symbol System Hypothesis
Latent Semantic Analysis (LSA). Introduction to LSA Learning Model Uses Singular Value Decomposition (SVD) to simulate human learning of word and passage.
Categorization  How do we organize our knowledge?  How do we retrieve knowledge when we need it?
Cognitive Psychology, 2 nd Ed. Chapter 8 Semantic Memory.
Chapter 5 Data mining : A Closer Look.
Radial Basis Function Networks
Lecture 10 – Semantic Networks 1 Two questions about knowledge of the world 1.How are concepts stored? We have already considered prototype and other models.
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.
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.
Processing of large document collections Part 2 (Text categorization) Helena Ahonen-Myka Spring 2006.
Emergence of Semantic Structure from Experience Jay McClelland Stanford University.
The changing face of face research Vicki Bruce School of Psychology Newcastle University.
Integrating New Findings into the Complementary Learning Systems Theory of Memory Jay McClelland, Stanford University.
The PDP Approach to Understanding the Mind and Brain J. McClelland Cognitive Core Class Lecture March 7, 2011.
2 2  Background  Vision in Human Brain  Efficient Coding Theory  Motivation  Natural Pictures  Methodology  Statistical Characteristics  Models.
Disintegration of Conceptual Knowledge In Semantic Dementia James L. McClelland Department of Psychology and Center for Mind, Brain, and Computation Stanford.
Emergence of Semantic Knowledge from Experience Jay McClelland Stanford University.
The Influence of Feature Type, Feature Structure and Psycholinguistic Parameters on the Naming Performance of Semantic Dementia and Alzheimer’s Patients.
Development, Disintegration, and Neural Basis of Semantic Cognition: A Parallel-Distributed Processing Approach James L. McClelland Department of Psychology.
Emergence of Semantic Structure from Experience Jay McClelland Stanford University.
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.
Chapter 11 Statistical Techniques. Data Warehouse and Data Mining Chapter 11 2 Chapter Objectives  Understand when linear regression is an appropriate.
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.
1 How is knowledge stored? Human knowledge comes in 2 varieties: Concepts Concepts Relations among concepts Relations among concepts So any theory of how.
Neural Networks Presented by M. Abbasi Course lecturer: Dr.Tohidkhah.
Origins of Cognitive Abilities Jay McClelland Stanford University.
The Emergent Structure of Semantic Knowledge
CSC321: Neural Networks Lecture 1: What are neural networks? Geoffrey Hinton
Emergent Semantics: Meaning and Metaphor Jay McClelland Department of Psychology and Center for Mind, Brain, and Computation Stanford University.
Semantic Knowledge: Its Nature, its Development, and its Neural Basis James L. McClelland Department of Psychology and Center for Mind, Brain, and Computation.
Organization and Emergence of Semantic Knowledge: A Parallel-Distributed Processing Approach James L. McClelland Department of Psychology and Center for.
Development and Disintegration of Conceptual Knowledge: A Parallel-Distributed Processing Approach James L. McClelland Department of Psychology and Center.
Adapted from by E.Day THE COGNITIVE APPROACH TYPES OF PROCESSING.
Structured Probabilistic Models: A New Direction in Cognitive Science
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
Bayesian inference in neural networks
Psychology 209 – Winter 2017 January 31, 2017
What is cognitive psychology?
Simple recurrent networks.
Psychology 209 – Winter 2017 Feb 28, 2017
Data Mining, Neural Network and Genetic Programming
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?
Backpropagation in fully recurrent and continuous networks
Emergence of Semantic Structure from Experience
Emergence of Semantics from Experience
Connecting Data with Domain Knowledge in Neural Networks -- Use Deep learning in Conventional problems Lizhong Zheng.
Artificial Intelligence 12. Two Layer ANNs
CLS, Rapid Schema Consistent Learning, and Similarity-weighted Interleaved learning Psychology 209 Feb 26, 2019.
Toward a Great Class Project: Discussion of Stoianov & Zorzi’s Numerosity Model Psych 209 – 2019 Feb 14, 2019.
Presentation transcript:

Contrasting Approaches To Semantic Knowledge Representation and Inference Psychology 209 February 15, 2013

The Nature of Cognition Many view human cognition as inherently –Structured –Systematic –Rule-governed We argue instead that cognition (and the domains to which cognition is applied) is inherently –Quasi-regular –Semi-systematic –Context sensitive

Emergent vs. Stipulated Structure Old London Midtown Manhattan

Natural vs. Stipulated Structure

Where does structure come from? It’s built in It’s learned from experience There are constraints built in that shape what’s learned – We all agree about this!

What is the nature of the constraints? Do they specify types of structural forms? – Kemp & Tenenbaum Or are they more generic? – Many other probabilistic models – Most work in the PDP framework Are they constraints on the process and mechanism? Or on the space of possible outcomes?

Outline The Rumelhart model of semantic cognition, and how it relates to probabilistic models of semantic cognition. Some claims it instantiates about the nature of semantic cognition that distinguish it from K&T – Data supporting these claims, and challenging K&T Toward a fuller characterization of what the Rumelhart model learns (and one of the things it can do that sustains our interest in it). Some future directions

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? 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

Distributed representations reflect different kinds of content in different areas Semantic dementia kills neurons in the temporal pole, and affects all kinds of knowledge We propose temporal pole as ‘hidden units’ mediating relations among properties in different modalities. Bi-directional connections between content-specific regions and temporal pole and recurrent connections [Medial temporal lobes provide a fast learning system for acquisition of new knowledge that may not be consistent with what is already known and as the site of initial storage of this knowledge.] language The Neural Basis of Semantic Cognition

Neural Networks and Probabilistic Models The Rumelhart model is learning to match the conditional probability structure of the training data: P(Attribute i = 1|Item j & Context k ) for all i,j,k The adjustments to the connection weights move them toward values than minimize a measure of the divergence between the network’s estimates of these probabilities and their values as reflected in the training data. It does so subject to strong constraints imposed by the initial connection weights and the architecture. – These constraints produce progressive differentiation, overgeneralization, etc. Depending on the structure in the training data, it can behave as though it is learning something much like one of K&T’s structure types, as well as many structures that cannot be captured exactly by any of the structures in K&T’s framework.

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 jk ) + (1-  k )[(  k-1 p(f i |c jk-1 ) + (1-  k-2 )[…])

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 a model that captures structure more organically.

An exploration of these ideas in the domain of mammals What is the best representation of domain content? How do people make inferences about different kinds of object properties?

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 –That is, there’s cross cutting structure that is not consistent with the hierarchy Property inferences for blank biological properties violate predictions of K&T’s tree model for weasels, hippos, and other animals

Applying the Rumelhart model to the mammals dataset Items Contexts Behaviors Body Parts Foods Locations Movement Visual Properties

Simulation Results We look at the model’s outputs and compare these to the structure in the training data. The model captures the overall and context specific structure of the training data The model progressively extracts more and more detailed aspects of the structure as training progresses

Simulation Output

Training Data

Network Output

Progressive PCs

Improving on the Naïve Bayes Classifier as a Model of the Rumelhart Model (with Andrew Saxe & Surya Ganguli) ItemsFeatures Items can be distributed patterns or localist units Target is the set of features as in the Rumelhart model but collapsed across contexts

SVD of a Simple Hierarchical Domain There can also be cross-cutting modes or semi-cross-cutting modes or even quasi-cross-cutting modes

Time course of learning Note the strong constraints imposed by the network on what is represented – this arises solely from the conservatism of learning rather than an explicit constraint on representation

Learning the Structure in the Training Data Progressive sensitization to successive singular dimensions captures learning of the mammals data set and other data sets as captured in the SVD of the input-output correlation matrix. This subsumes the naïve Bayes classifier as a special case when there is pure hierarchical structure (as in the Quillian training corpus), and also applies to a range of other types of structure (cross-cutting structure, linear structure, … ) The progressive learning of Singular dimensions is more generic, yet still very constraining, compared with other models. Question: Are PDP networks – and our brain’s neural networks – simply performing familiar statistical analyses? –Maybe neural networks can extend beyond what we generally envision in such analyses

Extracting Cross- Domain Structure

v

Input Similarity Learned Similarity

A Newer Direction Exploiting knowledge sharing across domains –Lakoff: Abstract cognition is grounded in concrete reality And this applies to mathematical cognition –Boroditsky: Cognition about time is grounded in our conceptions of space Can we capture these kinds of influences through knowledge sharing across contexts? Work by Thibodeau, Glick, Sternberg & Flusberg shows that the answer is yes

Summary Distributed representations provide the substrate for learned semantic representations that develop gradually with experience and degrade gracefully with damage The structure that is learned is organic rather than constrained to conform to any specific structure type. The SVD representation can capture much of this structure, but neural networks can go beyond this, e.g., exploiting second-order similarity. Structures of specific types should be seen as useful approximations rather than a procrustean bed into which actual knowledge must be thought of as conforming.