2 The Knowledge Level 2 . 1 Newell ’ s description of the knowledge level

This chapter develops a taxonomy of learning methods using techniques based on Newell’s knowledge level. Two properties of each system are defined: knowledge level predictability and knowledge level learning. A system is predictable at the knowledge level if the principle of rationality can be applied to predict its behavior. A system learns at the knowledge level if its knowledge level description changes over time. These two definitions can be used to generate the three-class taxonomy. The taxonomy formalizes the intuition that there are two kinds of learning systems: systems that simply improve their efficiency (symbollevel learning; SLL) and systems that acquire new knowledge (knowledge-level learning; KLL). The implications of the taxonomy for learning research are explored. Automatic programming research can provide ideas for SLL. Development of methods for KLL must rely either on the development of a principle of plausible rationality or on the construction of learning methods that work well only for certain kinds of environments. Explanation-based generalization and chunking methods address only SLL and do not provide solutions to the problems of KLL.

[1]  Thomas G. Dietterich.  Learning at the knowledge level , 2004, Machine Learning.

[2]  Richard M. Keller,et al.  Defining Operationality for Explanation-Based Learning , 1987, Artificial Intelligence.

[3]  Paul Compton,et al.  Inductive knowledge acquisition: a case study , 1987 .

[4]  Douglas H. Fisher,et al.  Improving Inference through Conceptual Clustering , 1987, AAAI.

[5]  Allen Newell,et al.  Knowledge Level Learning in Soar , 1987, AAAI.

[6]  William F. Clocksin,et al.  Programming in Prolog , 1987, Springer Berlin Heidelberg.

[7]  David W. Aha,et al.  Learning Representative Exemplars of Concepts: An Initial Case Study , 1987 .

[8]  M. Kearns,et al.  Recent Results on Boolean Concept Learning , 1987 .

[9]  Marianne Winslett,et al.  Is Belief Revision Harder Than You Thought? , 1986, AAAI.

[10]  Stuart J. Russell.  Preliminary Steps Toward the Automation of Induction , 1986, AAAI.

[11]  Thomas G. Dietterich,et al.  Selecting Appropriate Representations for Learning from Examples , 1986, AAAI.

[12]  Thomas G. Dietterich,et al.  Exploiting functional vocabularies to learn structural descriptions , 1986 .

[13]  Nils J. Nilsson,et al.  Probabilistic Logic * , 2022 .

[14]  Tom Michael Mitchell,et al.  Explanation-based generalization: A unifying view , 1986 .

[15]  Sridhar Mahadevan,et al.  Verification-based Learning: A Generalized Strategy for Inferring Problem-Reduction Methods , 1985, IJCAI.

[16]  William F. Clocksin,et al.  Programming in Prolog , 1981, Springer Berlin Heidelberg.

[17]  Leslie G. Valiant,et al.  A theory of the learnable , 1984, CACM.

[18]  N. Cocchiarella,et al.  Situations and Attitudes. , 1986 .

[19]  Richard M. Keller,et al.  Learning by Re-Expressing Concepts for Efficient Recognition , 1983, AAAI.

[20]  Paul D. Scott,et al.  Learning: The Construction of A Posteriori Knowledge Structures , 1983, AAAI.

[21]  Douglas B. Lenat,et al.  Why AM and EURISKO Appear to Work , 1984, Artif. Intell..

[22]  Herbert A. Simon,et al.  WHY SHOULD MACHINES LEARN , 1983 .

[23]  David J. Mostow,et al.  Machine Transformation of Advice Into a Heuristic Search Procedure , 1983 .

[24]  Tom M. Mitchell,et al.  Learning and Problem Solving , 1983, IJCAI.

[25]  Allen Newell,et al.  The Knowledge Level , 1989, Artif. Intell..

[26]  Tom M. Mitchell,et al.  Acquisition of Appropriate Bias for Inductive Concept Learning , 1982, AAAI.

[27]  Thomas G. Dietterich,et al.  Learning and Inductive Inference , 1982 .

[28]  Michael R. Genesereth,et al.  Metaphors and Models , 1980, AAAI.

[29]  Drew McDermott,et al.  Artificial intelligence meets natural stupidity , 1976, SGAR.

[30]  Allen Newell,et al.  Computer science as empirical inquiry: symbols and search , 1976, CACM.

[31]  Richard Fikes,et al.  Learning and Executing Generalized Robot Plans , 1993, Artif. Intell..

[32]  E. Mark Gold,et al.  Language Identification in the Limit , 1967, Inf. Control..