The Symbolic vs Subsymbolic Debate H. Bowman (CCNCS, Kent)
Dec 18, 2015
The Symbolic vs Subsymbolic Debate
H. Bowman
(CCNCS, Kent)
Disclaimer
• 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!!
The Mind-Body Problem
subsymbolic• inspired by neurobiology• how cognition emerges from
neurobiology
I am aCartesianDualist!
symbolic• putative characteristics of
cognition• information processing metaphor
The Symbolic Tradition
The 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
Key Assumptions
• Symbols are available to the cognitive system
• Symbol processing engine, characteristics,– Systematic, i.e. combinatorial symbol systems
and compositionality– Recursive knowledge structures
Syntax: Grammars 1
recursion
Sentence: S ::= NP VP
Noun phrase: NP ::= det AL N | N
Verb phrase: VP ::= V NP
Adjective list: AL ::= A AL | A
A set of “rules”
S, NP, VP, AL : molecules
det, N, V, A : atoms
Syntax: Grammars 2S
NP VP
det AL N V NP
the boy eats N
ice creamhappy
A
A Tree Data Structure
Compositionality
• 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]
Compositionality in Semantics 1
• Meanings of items plugged in as defined by syntax
MM[ John loves Jane ]=
MM[ John ] + MM[ loves ] + MM[ Jane ]+
composed together appropriately
M[ X ] denotes meaning of X
Compositionality in Semantics 2
• Same example in more detail
MM[ John loves Jane ]
=
……………………. . MM[ loves ] ..………..
MM[ John ] MM[ Jane ]
Compositionality in Semantics 3
• Meanings of atoms constant across different compositions
MM[ Jane loves John ]
=
……………………. . MM[ loves ] ..………..
MM[ Jane ] MM[ John ]
Compositionality in Semantics 4
• Also, meanings of molecules constant across different compositions
MM[ Jane loves John and Jane hates James ]
=
……..…..….……. ..…..….……. MM[ and ] ……….………..
MM[ Jane loves John ] MM[ Jane hates James ]
Compositionality in Semantics 5
MM[ Jane hates James and Jane loves John ]
=
……..…..….……. ..…..….……. MM[ and ] ……….………..
MM[ Jane loves John ]MM[ Jane hates James ]
Caveat
• Compositionality of course not absolute, e.g. Idioms: “kicked the bucket”
Compositionality: non-linguistic examples
• Not just an issue for language
• Reasoning / planning / deductive thought
• Representation of knowledge:– hierarchical / superordinate structures
From Marr’s theory ofobject Recognition
Representation of Visual Objects
Whole-part Hierarchies
S SS SS SS S S S S S S S SS SS SS S
Production 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
Symbol 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.
– Chomsky’s Universal Grammars
Symbol Systems and the Brain• For symbolists, the algorithmic / specification
levels are critical, the implementation level is insignificant (using Marr’s 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” [Fodor&Pylyshyn,88]
• A sort of compilation step.
• 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.” [Fodor&Pylyshyn,88]
The Sub-symbolic Tradition
Connectionism
• Inspiration from neurobiology
• Long tradition [at least from 50’s], e.g. Hebb, Rosenblatt, Grossberg, Rumelhart, McClelland, O’Reilly.
• Nodes, links, activation, weights, learning algorithms
Activation in Classic Artificial Neural Network Model
output - yj
net input - j
activationvalue - yjnode j
w1j w2j wnj
x1 x2 xn
inputs
ijii
wxj
integrate(weighted sum)
sigmoidalje
y j
11
Sigmoidal Activation Function
0
0.1
0.2
0.3
0.4
0.5
0.6
0.7
0.8
0.9
1
-4 -3 -2 -1 0 1 2 3 4net input ( )
ac
tiv
ati
on
(y)
Responsive around net input of 0
Unresponsive at extreme net inputs
Threshold: unresponsive at low net inputs
jey j
1
1
Connectionism 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
Example 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
A (Rather Naïve) Reading Model
A.1 B.1 Z.1 A.2 B.2 Z.2 A.3 B.3 Z.3 A.4 B.4 Z.4
/p/.1 /b/.1 /u/.1 /p/.2 /b/.2 /u/.2 /p/.3 /b/.3 /u/.3 /p/.4 /b/.4 /u/.4
SLOT 1ORTHOGRAPHY
PHONOLOGY
Connectionism & 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
Spectrum of Approaches
Systematic / symbolic
Unsystematic / subsymbolic
Distributed Representations / Back-prop., e.g. [Seidenberg]
Localist / Competitive Learning, e.g. IA model [McClelland]
Localist Models with Serial Order, e.g. Solaris [Davis]
Centralised Production SystemsArchitectures, e.g. SOAR [Newell]
Parallel Production Systems, e.g. EPIC [Kieras]
Hybrid Approaches, e.g. [Gabbay]
(Symbolic) Distributed Control, e.g. Actors [Hewett], Agents [Kokinov], ICS [Barnard], Society of Minds [Minsky]
• Introduction to connectionism– O’Reilly & 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
Possible Topics 1
• 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.
Possible Topics 2
References• 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.