The Syntactic Argument

The representation-without-rules conception of connectionism can't succeed, because rules can always be formulated to describe the network’s representation-level processing.



Such rules can:

  • specify how the parts of a representation are instantiated in nodes and connections (representation instantiation rules), and can
  • characterise the operation of individual nodes in the network (note-level rules).
Anticipated by Terence Horgan and John Tienson, 1991.
RELATED ARTICLESExplain
Artificial Intelligence
Can computers think? [1]
Yes: connectionist networks can think [5a]
Connectionist networks can think without following rules
Representations without rules
The Syntactic Argument
The Multiple Realisability Defence
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