emergence of semantics from experience

21
Emergence of Semantics from Experience Jay McClelland Department of Psychology and Center for Mind, Brain, and Computation Stanford University 1

Upload: guinevere-mckinney

Post on 31-Dec-2015

23 views

Category:

Documents


0 download

DESCRIPTION

Emergence of Semantics from Experience. Jay McClelland Department of Psychology and Center for Mind, Brain, and Computation Stanford University. 1. language. The Parallel Distributed Processing Approach to Semantic Cognition. - PowerPoint PPT Presentation

TRANSCRIPT

Page 1: Emergence of Semantics from Experience

Emergence of Semantics from Experience

Jay McClelland

Department of Psychology andCenter for Mind, Brain, and Computation

Stanford University

1

Page 2: Emergence of Semantics from Experience

• Representation is a pattern of activation distributed over neurons within and across brain areas.

• Bidirectional propagation of activation underlies the ability to bring these representations to mind from given inputs.

• The knowledge underlying propagation of activation is in the connections.

• Experience affects our knowledge representations through a gradual connection adjustment process

language

The Parallel Distributed Processing Approach to Semantic Cognition

2

Page 3: Emergence of Semantics from Experience

Distributed Representations:and Overlapping Patterns for Related

Concepts

dog goat hammer

dog goat hammer

3

Page 4: Emergence of Semantics from Experience

Emergence of Meaning in Learned Distributed Representations

• Learned distributed representations that capture important aspects of meaning emerge through a gradual learning process in simple connectionist networks

• The progression of learning captures several aspects of cognitive development:– Differentiation of Concepts– Illusory Correlations– Overgeneralization– And many other things

4

Page 5: Emergence of Semantics from Experience

5

Page 6: Emergence of Semantics from Experience

The Rumelhart Model

6

Page 7: Emergence of Semantics from Experience

The Training Data:

All propositions true of items at the bottom levelof the tree, e.g.:

Robin can {grow, move, fly}

7

Page 8: Emergence of Semantics from Experience

Target output for ‘robin can’ input

8

Page 9: Emergence of Semantics from Experience

aj

ai

wij

neti=ajwij

wki

Forward Propagation of Activation

9

Page 10: Emergence of Semantics from Experience

k ~ (tk-ak)

wij

i ~ kwki

wki

aj

Back Propagation of Error ()

Error-correcting learning:

At the output layer: wki = kai

At the prior layer: wij = jaj

ai

10

Page 11: Emergence of Semantics from Experience

11

Page 12: Emergence of Semantics from Experience

12

Page 13: Emergence of Semantics from Experience

Experience

Early

Later

LaterStill

13

Page 14: Emergence of Semantics from Experience

Why Does the Model Show Progressive Differentiation?

• Learning is sensitive to patterns of coherent covariation

• Coherent Covariation:

– The tendency for properties of objects to co-vary in clusters

• Figure shows attribute loadings on the principal dimensions of covariation. These capture:

– 1. Plants vs. animals– 2. Birds vs. fish– 3. Trees vs. flowers

• Same color = features that covary

• Diff color = anti-covarying features

14

Page 15: Emergence of Semantics from Experience

Trajectories of Concept Representations During Differentiation

15

Page 16: Emergence of Semantics from Experience

Illusory Correlations

16

Page 17: Emergence of Semantics from Experience

A typical property thata particular object lackse.g., pine has leaves

An infrequent,atypical property

17

Page 18: Emergence of Semantics from Experience

Overgeneralization of Frequent Names to Similar Objects

“dog”

“goat”“tree”

18

Page 19: Emergence of Semantics from Experience

19

Page 20: Emergence of Semantics from Experience

Other Applications of the Model

• Expertise effects

• Conceptual reorganization

• Effects of language and culture

• Effects of brain damage:

– Loss of differentiation– Overgeneralization in

object naming– Illusory correlations

camel swan 20

Page 21: Emergence of Semantics from Experience

Conclusion

• We represent objects using patterns of activity over neuron-like processing units

• These patterns depend on connection weights learned through experience

• Differences in experience lead to differences in conceptual representations.

21