Inductive Learning

• 作 者: 吴信东
• 机 构: Department of Artificial Intelligence University of Edinburgh,80 South Bridge,Edinburgh EHI IHN,UK,
• 出 处: Journal of Computer Science and Technology
• 发表日期: 1993年02期
• 关键词: bases inductive noisy widespread satisfactory intelligence avoiding attribute ge

Machine learning(ML)is a major subfield of artificial intelligence(AI).It has been seen as a feasi-ble way of avoiding the knowledge bottleneck problem in knowledge-based systems development.Re-search on ML has concentrated in the main on inductive learning,a paradigm for inducing rules fromunordered sets of exmaples.AQ11 and ID3,the two most widespread algorithms in ML,are both induc-tive.This paper first summarizes AQ11,ID3 and the newly-developed extension matrix approach basedHCV algorithm;and then reviews the recent development of inductive learing and automatic knowledgeacquisition from data bases.

Machine learning (ML) is a major subfield of artificial intelligence (AI) .It has been seen as a feasi- ble way of avoiding the knowledge bottleneck problem in knowledge-based systems development. Re-search on ML has concentrated in the main on inductive learning, a paradigm for inducing rules from unitized sets of exmaples. AQ11 and ID3, the two most widespread algorithms in ML, are both induc- tive. This paper first summarizes AQ11, ID3 and the newly-developed extension matrix approach based HCV algorithm; and then reviews the recent development of inductive learing and automatic knowledge acquisition from data bases.