Too much representation, not enough dynamics

Connectionists are right to emphasise dynamics and complex activity patterns, but subsymbolic representation carries connotations not found in animal neural dynamics, and ignores the limit cycles and chaos found in animal neural dynamics.

Connectionists like Smolensky are right to emphasise dynamics and complex activity patterns. However, Smolensky's notion of subsymbolic representation carries connotations—of registration, storage, retrieval, and backpropagation—that do not appear to play a role in the complex neural dynamics of animals, like rabbits.

Furthermore, connectionists rely too heavily on the simple dynamics of equilibrium attractors. In doing so, they ignore the more complex dynamics of limit cycles and chaos, which play important roles in the neural dynamics of animals.

Walter Freeman, 1988
RELATED ARTICLESExplain
Artificial Intelligence
Can computers think? [1]
Yes: connectionist networks can think [5a]
The Subsymbolic Paradigm
Too much representation, not enough dynamics
Common sense and connectionism
The sensorimotor system
Between-module structures
Connectionist networks can’t elaborate capacities quickly
Smolensky's treatment of levels is problematic
Statistical rationality needed
Symbolic processing in specially crafted networks
Graph of this discussion
Enter the title of your article


Enter a short (max 500 characters) summation of your article
Enter the main body of your article
Lock
+Comments (0)
+Citations (0)
+About
Enter comment

Select article text to quote
welcome text

First name   Last name 

Email

Skip