Explanation and Collective Computation

		/vol02/explain/	© Copyright 1995
		Volume 02	Received: Accepted:	---- ----

Explanation and Collective Computation Joachim Diederich and Alan B. Tickle
Abstract
	User explanation is an important function in artificial intelligence (AI) and in artificial neural networks (ANNs). Experience with expert systems and neural networks has shown that the ability to generate explanations is absolutely crucial for user acceptance. ANNs traditionally have had difficulties with generating explanation structures [1]. However, recent results on knowledge insertion (or knowledge initialisation), rule refinement and rule extraction from ANNs indicate that this problem is about to be solved. The objective of this paper is to discuss the problem of generating explanations in neural networks and systems using collective computation. The problem is that in conventional systems, explanation structures are based on intermediate states in processing which can be interpreted. In systems where intermediate states are a function of the initial parameters (for example, weights in a neural network) this is naturally a problem.

Full Text

Multimedia Links
(none)

Reference Links
(none)

Citation Reference

Get viewers
for PS & PDF

[CI Editor] [Site Manager]