Experiential learning in analogical problem solving
作者： Jaime G. Carbonell
DOI:
关键词:
摘要: A computational model of skill acquisition is analyzed based on extensions to an analogical problem solving method and previous Al work concept acquisition. The present investigation focuses exploiting extending the reasoning generate useful exemplary solutions related problems from which more general plans can be induced refined. Starting with a inference engine, experience is, in essence, compiled incrementally into effective procedures that solve various classes reliable direct manner.
参考文章(16)
Jaime G. Carbonell, A computational model of analogical problem solving international joint conference on artificial intelligence. pp. 147- 152 ,(1981)
Richard Edward Cullingford, Script application: computer understanding of newspaper stories. [National Technical Information Service, U.S. Dept. of Commerce]. ,(1977)
Patrick H. Winston, Learning Structural Descriptions From Examples The Psychology of Computer Vision. ,(1970)
P. S. Rosenbloom, A. Newell, Mechanisms of skill acquisition and the law of practice The Soar papers (vol. 1). pp. 81- 135 ,(1993)
Tom Michael Mitchell, None, Version spaces: an approach to concept learning. Stanford University. ,(1979)
Jaime G Carbonell, Metaphor : an inescapable phenomenon in natural language comprehension ,(1981)
Jaime G. Carbonell, Learning by Analogy: Formulating and Generalizing Plans from Past Experience Machine Learning. pp. 137- 161 ,(1983) , 10.1007/978-3-662-12405-5_5
Thomas G. Dietterich, Ryszard S. Michalski, Inductive learning of structural descriptions: Evaluation criteria and comparative review of selected methods Artificial Intelligence. ,vol. 16, pp. 257- 294 ,(1981) , 10.1016/0004-3702(81)90002-3
Frederick Hayes-Roth, John McDormott, Knowledge acquisition from structural descriptions international joint conference on artificial intelligence. pp. 356- 362 ,(1977)
Yuichiro Anzai, Herbert A. Simon, The theory of learning by doing Psychological Review. ,vol. 86, pp. 124- 140 ,(1979) , 10.1037/0033-295X.86.2.124