The extremist fallacy

Opponents assume there are only two positions on the connectionism/symbolism issue: eliminativism and implementationism—and that to support one is to reject the other. The subsymbolic paradigm rejects both, forging a "limitivist" middle road.

A common problem with the various attacks on the three level distinction is that they commit the following extremist fallacy: there are only two positions on the connectionism/symbolism issue: eliminativism and implementationism. Any view that rejects one must embrace the other; if it embraces both, it is incoherent. But the subsymbolic paradigm rejects both eliminativism and implementationism, forging a "limitivist" middle road.

Smolensky (1988b).

Note: Smolenksy separately address the various other attacks on his treatment of levels—but these arguments are not described on the original Horn map.
RELATED ARTICLESExplain
Artificial Intelligence
Can computers think? [1]
Yes: connectionist networks can think [5a]
The Subsymbolic Paradigm
Smolensky's treatment of levels is problematic
The extremist fallacy
Better ways to articulate the levels distinction
Conceptual and subconceptual part-whole relationship
Contact between levels is closer than suggested
Flawed analogy between Newtonian and Quantum physics
Insufficient focus on the neural level
Levels are nothing but pragmatic constructs
Pursues a limited and limiting goal
Three level distiction is inchoerent
Three-level distinction is too simple
Treatment of levels is Eliminativist
Treatment of levels is implementationist
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