Learning object-level and meta-level knowledge in expert systems

Thesis/Dissertation · Tue Jan 01 04:00:00 EST 1985

OSTI ID:5424026

Fu, L M

A high performance expert system can be built by exploiting machine learning techniques. A learning model has been designed and implemented that is capable of constructing a knowledge base, in the form of rules, from a case library and continuously updating it to accommodate new facts. This model is designed primarily for EMYCIN-like systems in which there is uncertainty about data as well as about the strength of inference and in which the rules chain together to infer complex hypothesis. These features greatly complicate the learning problem. In machine learning, two issues that cannot be overlooked practically are efficiency and noise. A subprogram, called CONDENSER, is designed to remove irrelevant features during learning and improve the efficiency. The noise can be handled by optimizing the result to achieve minimal prediction errors. Another subprogram was developed to learn meta-level rules. Using the ideas developed in this work, an expert program called JAUNDICE was built, which can diagnose the likely disease and mechanisms of a patient with jaundice.

• Research Organization: Stanford Univ., CA (USA)
• OSTI ID: 5424026
• Country of Publication: United States
• Language: English

Related Subjects

551000 -- Physiological Systems
59 BASIC BIOLOGICAL SCIENCES
99 GENERAL AND MISCELLANEOUS
990200* -- Mathematics & Computers
ARTIFICIAL INTELLIGENCE
DIAGNOSIS
EFFICIENCY
EXPERT SYSTEMS
JAUNDICE
LEARNING
MAN-MACHINE SYSTEMS
MATHEMATICAL MODELS
NOISE
PATHOLOGICAL CHANGES
SYMPTOMS