Cognitive Science

1
Cognitive Science

• Introduction

2
Overview

• Aims and learning outcomes
• Assessment
• Programme
• Cognitive science is interdisciplinary
• Cognitive science uses formal models
• Beware
• This strategy might not succeed (!)
• Fashion can influence the perception of research

3
Aims

• To introduce interdisciplinary approaches to the
  study of higher cognitive processes
• To familiarise you with computational and other
  formal modelling
• To illustrate the application of modelling to
  cognitive processes

4
Learning outcomes

• To gain direct experience of computational and
  other formal modelling techniques.
• To integrate material across areas within
  psychology and across traditional subject
  disciplines.
• To compare and critically evaluate formal
  techniques in relation to empirical findings.
• To tackle key theoretical problems in cognitive
  science, particularly problems linked by the
  theme of common sense reasoning.

5
Assessment

• Two hour examination in June, which counts for
  two thirds of the mark.
• Three pieces of coursework (counting for 4, 4,
  and 25 respectively of the course mark)
• Coursework assesses the first and, to a lesser
  degree, the third learning objectives.
• The exam will assess learning objectives two,
  three and four.

6
Coursework

• AW 1 - Connectionist modelling 1 (4)
• AW 2 - Connectionist modelling 2 (4)
• Modelling project (25)

7
Programme

• 1 Introduction - why cognitive science?
• 2 Cognitive modelling
• 3 Cognitive modelling
• 4 Cognitive modelling
• 5 Cognitive modelling
• 6 The development of concepts
• 7 Learning word meanings
• 8 Ambiguous words
• 9 Compositionality and word meaning
• 10 Common-sense reasoning

8
Cognitive Modelling

• Project construct a model of adjective-noun
  combination
• red apple
• fake gun
• heavy baby / heavy elephant

9
Cognitive Modelling
Learns by training over and over
Heavy baby
NODES nodes 4 inputs 6 outputs 2 output
nodes are 1-4 CONNECTIONS 1-4 from i1 i6
Distributed 3 .7 .3 .4 .6 .5 .9 .4 .6 .6 .5 .2 .2
Baby
Heavy
Distributed 3 .2 .3 .7 .2 .4 .6 .2 .3 .5 .8 .4
.6 .2 .3 .6 .4 .2 .2
10
The development of concepts

• What do we mean concept?
• Why is concept learning tricky to understand?
• Connectionist nets as a simple model of concept
  learning
• Some features of natural concept learning that
  make the picture less simple
• e.g. Role of existing background knowledge

11
Learning word meanings

• Gavagai

12
Ambiguity and vagueness

• Complex links between words and concepts
• Bank
• Newspaper
• To paint

13
Combining concepts

• Compositionality is key to language
• red apple, red brick, red mist
• Watergate, blood gate, Stargate

14
Commonsense reasoning

• Which information is relevant to drawing a
  conclusion?
• Which facts are affected by an event?
• Yale shooting problem
• Property inheritance
• Tweety is a bird. So, Tweety can fly?

15
A little history the Cognitive Revolution

• Skinner (1957)
• Children learn words (language) through
  operant conditioning
• - stimulus controls response
• Chomsky's (1959) review of Verbal Behavior
• (link on course web pages)
• "Dutch" - what stimulus? proliferate
  "stimuli
• but role of attention etc. ? mind
• 'Creativity' of language ? compositionality

16

• Technical concepts of Skinner's behaviorism
  (stimulus, reinforcement, operant etc.) were used
  non-technically in "Verbal Behavior
• Eg. the artist is reinforced by the effects his
  work may have on others
• but the artist's (often) not there when these
  effects occur. It's not like reinforcement in a
  Skinner box.

17

• "I now believe that mind is something more than a
  four letter Anglo-Saxon word - human minds exist
  and it is our job as psychologists to study
  them."
• Miller (1962) in American Psychologist, 17, p.
  761
• Nb Piaget, even Freud, were always cognitively
  oriented

18
Chomsky (1957 1965)Transformational Generative
Grammar

• Account for syntactic facts (linguistics)
• e.g. active and passive have same meaning
• Judge facts using 'intuitions' (psychology)
• ? the resulting grammars are related to something
  people know
• (linguistic competence)

19
A small transformational generative grammar

• S ? NP, VP
• NP ? determiner, noun
• VP ? verb, NP
• determiner the, a noun boy, dog verb eat,
  kick, bite, occur
• Passive transformation (simplified)
• NP1, V, NP2 ? NP2, BE, V, EN, by, NP1
• Captures the fact that selection restrictions
  match
• Congress impeaches Clinton Charlie impeaches a
  shoe
• Clinton is impeached by Congress A shoe is
  impeached

20

• Congress impeaches Clinton
• NP1 V NP2
• Rule
• NP1, V, NP2 ? NP2, BE, V, EN, by, NP1
• Clinton is impeached by Congress

21
More history early machine translation

• Weaver (1949) memorandum
• Georgetown (1954-66)
• 250 words 6 rules at start
• Alpac Commission (1966)
• speed? cost? quality?
• Meteo (1977)
• English ? French
• Use existing materials (style sheets)
• Translators involved

22
Fashion and the life cycle of (some) AI projects

• Oblivion, fading ? Rebirth ? Excitement ? Claims
  ? More excitement ? Wild claims ? Unmet
  expectations
• ? Fading, oblivion.

23
Cognitive science now

• "higher" cognitive functions processes
  representations
• Interdisciplinary
• Psychology, linguistics, philosophy, computer
  science, brain sciences, anthropology, .
• Use formal / explicit models
• Computational metaphor
• strong v. weak

24

• The original question "Can machines think? I
  believe to be too meaningless to deserve
  discussion.
• Alan Turing
• www.warwick.ac.uk/psrex/cogsci.html

25

• The end