Learning perceptual schemas to avoid the utility problem

This paper describes principles for representing and organising planning knowledge in a machine learning architecture. One of the difficulties with learning about tasks requiring planning is the utility problem: as more knowledge is acquired by the learner, the utilisation of that knowledge takes on a complexity which overwhelms the mechanisms of the original task. This problem does not, however, occur with human learners: on the contrary, it is usually the case that, the more knowledgeable the learner, the greater the efficiency and accuracy in locating a solution. The reason for this lies in the types of knowledge acquired by the human learner and its organisation. We describe the basic representations which underlie the superior abilities of human experts, and describe algorithms for using equivalent representations in a machine learning architecture.

[1]  Herbert A. Simon,et al.  Five seconds or sixty? Presentation time in expert memory , 2000 .

[2]  Peter C.-H. Cheng.  Scientific Discovery With Law-Encoding Diagrams , 1996 .

[3]  D. Goldstein,et al.  Mind as computer: Birth of a metaphor , 1996 .

[4]  Susanne P. Lajoie,et al.  Computers As Cognitive Tools , 2020 .

[5]  Fernand Gobet,et al.  Memory for the meaningless: How chunks help , 1998 .

[6]  Steven Minton,et al.  Quantitative Results Concerning the Utility of Explanation-based Learning , 1988, Artif. Intell..

[7]  H. Simon,et al.  Perception in chess , 1973 .

[8]  Marvin Minsky,et al.  A framework for representing knowledge , 1974 .

[9]  R. Shillcock,et al.  Proceedings of the Twenty-Sixth Annual Conference of the Cognitive Science Society , 1998 .

[10]  Herbert A. Simon,et al.  CaMeRa: A Computational Model of Multiple Representations , 1997, Cogn. Sci..

[11]  H. Simon,et al.  EPAM-like Models of Recognition and Learning , 1984, Cogn. Sci..

[12]  Herbert A. Simon,et al.  Why a Diagram is (Sometimes) Worth Ten Thousand Words , 1987, Cogn. Sci..

[13]  Patrick Henry Winston,et al.  The psychology of computer vision , 1976, Pattern Recognit..

[14]  Michael Lebowitz,et al.  Experiments with incremental concept formation: UNIMEM , 2004, Machine Learning.

[15]  LebowitzMichael.  Experiments with Incremental Concept Formation , 1987 .

[16]  John Sweller,et al.  Cognitive Load During Problem Solving: Effects on Learning , 1988, Cogn. Sci..

[17]  John R. Anderson,et al.  Abstract Planning and Perceptual Chunks: Elements of Expertise in Geometry , 1990, Cogn. Sci..

[18]  Peter C-H.  A Framework for Scientific Reasoning with Law Encoding Diagrams: Analysing Protocols to Assess Its Utility , 1998 .

[19]  H. Simon,et al.  A simulation of memory for chess positions. , 1973 .

[20]  David E. Kieras.  Learning Schemas from Explanations in Practical Electronics , 1993 .

[21]  Fernand Gobet.  Discrimination nets, production systems and semantic networks: elements of a unified framework , 1996 .