Some recent work in artificial intelligence
- 1 January 1966
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in Proceedings of the IEEE
- Vol. 54 (12) , 1687-1697
- https://doi.org/10.1109/proc.1966.5250
Abstract
This paper will review certain approaches to artifical intelligence research--mainly work done since 1960. An important area of research involves designing a machine that can adequately improve its own performance as well as solve other problems normally requiring human intelligence. Work in heuristic programming that seems most relevant to this goal will be discussed at length. Important subproblems are devising techniques for self-improvement, the general problem of deciding what task to best work on next in a network of tasks, and the general problem of how to mechanize learning or inductive inference. Some work in linguistics and pattern recognition is directly concerned with the induction problem. Another area of research that will be treated is simulation of organic evolution.Keywords
This publication has 26 references indexed in Scilit:
- How a computer system can learnIEEE Spectrum, 1964
- A formal theory of inductive inference. Part IIInformation and Control, 1964
- Programs for machine learning. Part IIInformation and Control, 1964
- Pattern-string learning programsBehavioral Science, 1964
- Programs for machine learning Part IInformation and Control, 1962
- Self-Organizing Systems-A Review and CommentaryProceedings of the IRE, 1961
- Steps toward Artificial IntelligenceProceedings of the IRE, 1961
- Some Studies in Machine Learning Using the Game of CheckersIBM Journal of Research and Development, 1959
- A Learning Machine: Part IIIBM Journal of Research and Development, 1959
- Pattern recognition and modern computersPublished by Association for Computing Machinery (ACM) ,1955