论文信息 - What is a deep expert system? An analysis of first-generation limitations and a review of second-generation architectures

What is a deep expert system? An analysis of first-generation limitations and a review of second-generation architectures

Abstract First-generation expert systems have significant limitations, attributed to their not being sufficiently deep . This paper attempts to clarify the concept of deepness with respect to expert systems, by analysing the limitations of first-generation expert systems and reviewing proposed architectures for second-generation expert systems. Inherent in each architecture is a definition of deepness.

Elpida T. Keravnou

[1] Elpida T. Keravnou,et al. Competent Expert Systems: A Case Study in Fault Diagnosis , 1986 .

[2] Ramesh S. Patil,et al. Causal representation of patient illness for electrolyte and acid-base diagnosis , 1981 .

[3] Joe W. Duran,et al. A General Expert System Design for Diagnostic Problem Solving , 1984, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[4] W Van de Velde. Learning heuristics in second generation expert systems , 1987 .

[5] Elpida T. Keravnou,et al. Deep and shallow models in medical expert systems , 1989, Artif. Intell. Medicine.

[6] Randall Davis,et al. Reasoning from First Principles in Electronic Troubleshooting , 1983, Int. J. Man Mach. Stud..

[7] Peter E. Hart,et al. Directions for AI in the eighties , 1982, SGAR.

[8] B. Chandrasekaran,et al. Conceptual Representation of Medical Knowledge for Diagnosis by Computer: MDX and Related Systems , 1983, Adv. Comput..

[9] Luc Steels,et al. Components of Expertise , 1990, AI Mag..