comments

Statistical rationality needed

Smolensky needs to describe the subsymbolic paradigm more precisely by stressing the role of statistical reference in connectionist systems.

To do this, Smolensky has to recognise that:

  • logical inference is a special case of statistical reference;
  • rational connectionits models are statistical inference mechanisms;
  • continuity is necessary to representing partial (real-valued) beliefs.
Richard Golden, 1988, p.35.
RELATED ARTICLESExplain
⌅
Artificial Intelligence
⌃
Can computers think? [1]
⌃
Yes: connectionist networks can think [5a]
⌃
The Subsymbolic Paradigm
■
Statistical rationality needed
↳
Too early to throw out computational approaches
□
Common sense and connectionism
□
The sensorimotor system
□
Between-module structures
□
Connectionist networks can’t elaborate capacities quickly
□
Smolensky's treatment of levels is problematic
□
Symbolic processing in specially crafted networks
□
Too much representation, not enough dynamics
□
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