Title: The Symbolic vs Subsymbolic Debate
1The Symbolic vs Subsymbolic Debate
2Disclaimer
- Serious simplification of a complex debate.
- Emphasize extreme positions to clarify basic
points of controversy. - What I present is not necessarily what I
personally believe!!
3The Mind-Body Problem
- symbolic
- putative characteristics of cognition
- information processing metaphor
- subsymbolic
- inspired by neurobiology
- how cognition emerges from neurobiology
4The Symbolic Tradition
5The Computer Metaphor
- Takes inspiration from,
- programming languages computational logic
- data structures knowledge representation
- link to programming langs. such as Lisp Prolog
- computer architectures
- Von Neumann architectures centralized processing
- computability theory
- the Church Turing hypothesis
6Key Assumptions
- Symbols are available to the cognitive system
- Symbol processing engine, characteristics,
- Systematic, i.e. combinatorial symbol systems and
compositionality - Recursive knowledge structures
7Syntax Grammars 1
A set of rules
Sentence S NP VP Noun phrase
NP det AL N N Verb phrase VP V
NP Adjective list AL A AL A
S, NP, VP, AL molecules det, N, V, A atoms
8Syntax Grammars 2
S
A Tree Data Structure
9Compositionality
- Plug constituents in according to rules
- Structure of expressions indicates how they
should be interpreted - Semantic Compositionality,
- the semantic content of a (molecular)
representation is a function of the semantic
contents of its syntactic parts, together with
its constituent structure - Fodor Pylyshyn,88
10Compositionality in Semantics 1
- Meanings of items plugged in as defined by syntax
M X denotes meaning of X
M John loves Jane M John M loves
M Jane composed together appropriately
11Compositionality in Semantics 2
- Same example in more detail
M John loves Jane . M loves
....
M John
M Jane
12Compositionality in Semantics 3
- Meanings of atoms constant across different
compositions
M Jane loves John . M loves
....
M Jane
M John
13Compositionality in Semantics 4
- Also, meanings of molecules constant across
different compositions
M Jane loves John and Jane hates James
...... M and ...
M Jane loves John
M Jane hates James
14Compositionality in Semantics 5
M Jane hates James and Jane loves John
...... M and ...
M Jane loves John
M Jane hates James
15Caveat
- Compositionality of course not absolute, e.g.
Idioms kicked the bucket
16Compositionality non-linguistic examples
- Not just an issue for language
- Reasoning / planning / deductive thought
- Representation of knowledge
- hierarchical / superordinate structures
17Representation of Visual Objects
From Marrs theory of object Recognition
18Whole-part Hierarchies
S S S
S S S S S S S S S S S
S S S S
S S S
19Production System Architectures of the Mind
- Most detailed and complete realisation of
symbolic tradition, e.g. - SOAR (Unified Theories of Cognition) Newell
- ACT-R Anderson
- EPIC Kieras
- GOFAI (Good Old Fashioned Artificial
Intelligence) - Based upon expert systems technology
20Symbol Systems and Nature vs Nurture
- Learning theories of symbolic architectures are
rather limited - although, chunking-based theories do exist
- Where does the symbolic processing engine come
from? - THEREFORE
- Evolutionary explanations, e.g.
- Chomskys Universal Grammars
21Symbol Systems and the Brain
- For symbolists, the algorithmic / specification
levels are critical, the implementation level is
insignificant (using Marrs terminology) - for a Symbolist, neurons implement all
cognitive processes in precisely the same way,
viz., by supporting the basic operations that are
required for symbol-processing i.e. all
that is required is that you use your neural
network to implement a Turing machine
FodorPylyshyn,88 - A sort of compilation step.
22- Computers used as an analogy, where software is
the interesting thing and the hardware mapping is
fixed and automatic. - one should be deeply suspicious of the heroic
sort of brain modelling that purports to address
the problems of cognition. We sympathize with the
craving for biologically respectable theories
that many psychologists seem to feel. But, given
a choice, truth is more important than
respectability. FodorPylyshyn,88
23The Sub-symbolic Tradition
24Connectionism
- Inspiration from neurobiology
- Long tradition at least from 50s, e.g. Hebb,
Rosenblatt, Grossberg, Rumelhart, McClelland,
OReilly. - Nodes, links, activation, weights, learning
algorithms
25Activation in Classic Artificial Neural Network
Model
output - yj
activation value - yj
node j
net input - hj
26Sigmoidal Activation Function
Responsive around net input of 0 Unresponsive at
extreme net inputs Threshold unresponsive at
low net inputs
27Connectionism and Nature vs Nurture
- Powerful learning algorithm
- directed weight adjustment
- extracting regularities (Hebbian learning)
- supervised learning (Back-propagation)
- Typically ascribe more to learning than to
evolution
28Example Connectionist Model
- Word reading as an example
- Orthography to Phonology
- Words of four letters or less
- Need to represent order of letters, otherwise,
e.g. slot and lots the same - Slot coding
29A (Rather Naïve) Reading Model
PHONOLOGY
ORTHOGRAPHY
30Connectionism Compositionality
- Highly non-compositional, e.g.
- a in ant and cat completely unrelated
representations - no sense to which plug in constituent
representations - maximally affected by context
- Same argument would generalise to semantic
compositionality - Alternative connectionist models do better, e.g.
activation gradient models, but not clear that
any model is truly systematic in sense of
symbolic processing
31Spectrum of Approaches
Systematic / symbolic
Centralised Production Systems Architectures,
e.g. SOAR Newell
Parallel Production Systems, e.g. EPIC Kieras
(Symbolic) Distributed Control, e.g. Actors
Hewett, Agents Kokinov, ICS Barnard,
Society of Minds Minsky
Hybrid Approaches, e.g. Gabbay
Localist Models with Serial Order, e.g. Solaris
Davis
Localist / Competitive Learning, e.g. IA model
McClelland
Distributed Representations / Back-prop., e.g.
Seidenberg
Unsystematic / subsymbolic
32Possible Topics 1
- Introduction to connectionism
- OReilly Munakata, 2000
- Production system architectures
- ACT-R Anderson,93
- Connectionism Strengths and Weaknesses
- Fodor Pylyshyn, 88
- McClelland, 92 and 95
- Symbolic-like Connectionism
- Hinton, 90
33Possible Topics 2
- Past tense debate
- Pinker et al, 2003
- Localist vs distributed debate
- Bowers, 2002 and Page, 2000.
- Dual process theory system 1 (neural) system
2 (symbolic) - Evans, 2003.
34References
- Anderson, J. R. (1993). Rules of the Mind.
Hillsdale, NJ Erlbaum. - Bowers, J. S. (2002). Challenging the widespread
assumption that connectionism and distributed
representations go hand-in-hand. Cognitive
Psychology., 45, 413-445. - Evans, J. S. B. T. (2003). In Two Minds Dual
Process Accounts of Reasoning. Trends in
Cognitive Sciences, 7(10), 454-459. - Fodor, J. A., Pylyshyn, Z. W. (1988).
Connectionism and Cognitive Architecture A
Critical Analysis. Cognition, 28, 3-71. - Hinton, G. E. (1990). Special Issue of Journal
Artificial Intelligence on Connectionist Symbol
Processing (edited by Hinton, G.E.). Artificial
Intelligence, 46(1-4). - O'Reilly, R. C., Munakata, Y. (2000).
Computational Explorations in Cognitive
Neuroscience Understanding the Mind by
Simulating the Brain. MIT Press. - McClelland, J. L. (1992). Can Connectionist
Models Discover the Structure of Natural
Language? In R. Morelli, W. Miller Brown, D.
Anselmi, K. Haberlandt D. Lloyd (Eds.), Minds,
Brains and Computers Perspectives in Cognitive
Science and Artificial Intelligence (pp.
168-189). Norwood, NJ. Ablex Publishing Company. - McClelland, J. L. (1995). A Connectionist
Perspective on Knowledge and Development. In J.
J. Simon G. S. Halford (Eds.), Developing
Cognitive Competence New Approaches to Process
Modelling (pp. 157-204). Mahwah, NJ Lawrence
Erlbaum. - Page, M. P. A. (2000). Connectionist Modelling in
Psychology A Localist Manifesto. Behavioral and
Brain Sciences, 23, 443-512. - Pinker, S., Ullman, M. T., McClelland, J. L.,
Patterson, K. (2002). The Past-Tense Debate
(Series of Opinion Articles). Trends Cogn Sci,
6(11), 456-474.