Please use this identifier to cite or link to this item:
Title: Making deepness explicit
Authors: Washbrook, John
Keravnou-Papailiou, Elpida
Keywords: Computer science;Artificial intelligence;Medicine;Expert systems (Computer science)
Issue Date: 1990
Publisher: Elsevier
Source: Artificial intelligence in medicine, 1990, Volume 2, Issue 3, Pages 129–134
Abstract: The concept of deepness is a useful, if poorly defined, concept. In spite of the development over a number of years of several medical expert systems with high levels of performance, these systems have failed in that they have not been accepted by the medical community. The introduction of so-called deep systems, where deepness is often taken to be synonymous with embodying causality, was an approach to resolving this problem. Two systems, CASNET and NEOMYCIN, are compared and it is argued that although CASNET is deeper in that its reasoning is causal, NEOMYCIN is in fact more acceptable in that its explanations and dialogue are closer to those of an expert. The intuitive meaning of deepness is discussed, and a working definition is developed which is not based exclusively upon causality, but which includes the explicit representation of strategic and factual knowledge
ISSN: 09333657
Rights: © 1990 Published by Elsevier B.V.
Type: Article
Appears in Collections:Άρθρα/Articles

Show full item record

Citations 20

checked on Feb 13, 2018

Page view(s)

Last Week
Last month
checked on Nov 13, 2018

Google ScholarTM



Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.