Connectionist representations avoid the dilemma

Connectionist representations can exhibit systematicity and related phenomena without implementing a classical symbolic architecture.

Systematicity & Related Phenomena
 
Systematicity

The ability to think certain thoughts (or certain to say certain things) is intrinsically connected to the ability to think certain other thoughts (or to say other things). Systematicity can also be characterised as a kind of mental symmetry.

A related point is that systematically related thoughts are not related to certain other thoughts. For example, "John loves Sally" is systematically related to "Sally loves John" but not to "two plus two equals four".

This property of cognitive systems is so closely linked to systematicity that is often overlooked. It has been called compositionality, but this term is confusing, because compositionality is normally used to refer to the compositional structure of mental states (see sidebar, "Constituent structure of mental representations" on this map).

Inferential Coherence

The ability to make certain inferences is related to the ability to make certain others. For xample, an organism that can infer p from p & q can also infer q from p & q. This is also called systematicity of inference.

Productivity

From a finite stock of resources, a person can think of an indefinite number of thoughts (for, say, an indefinite number of things) by combining atomic and molecular representations in various ways. This is also known as generativity.
RELATED ARTICLESExplain
Artificial Intelligence
Can computers think? [1]
Yes: connectionist networks can think [5a]
The Connectionist Dilemma
Connectionist representations avoid the dilemma
Functionally compostional representations
Tensor product representations
The Coffee Story
Unstructured representations account for systematicity
Spatial distribution is inadequate
Burden of proof is on connectionism
Connectionism is associationism
Cognition isn’t always systematic
Connectionist machines possess compositional semantics
Systematicity explained by natural selection
Systematicity is a conceptual not empirical law
Systematicity not enough to argue for classicism
The Three-Concept Monte
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