Learning at the Knowledge Level

When Newell introduced the concept of the knowledge level as a useful level of description for computer systems, he focused on the representation of knowledge. This paper applies the knowledge level notion to the problem of knowledge acquisition. Two interesting issues arise. First, some existing machine learning programs appear to be completely static when viewed at the knowledge level. These programs improve their performance without changing their ‘knowledge.’ Second, the behavior of some other machine learning programs cannot be predicted or described at the knowledge level. These programs take unjustified inductive leaps. The first programs are called symbol level learning (SLL) programs; the second, nondeductive knowledge level learning (NKLL) programs. The paper analyzes both of these classes of learning programs and speculates on the possibility of developing coherent theories of each. A theory of symbol level learning is sketched, and some reasons are presented for believing that a theory of NKLL will be difficult to obtain.

[1]  Tom M. Mitchell,et al.  The Need for Biases in Learning Generalizations , 2007 .

[2]  Robert J. Melosh,et al.  Structural Analysis of Solids , 1963 .

[3]  Kurt VanLehn,et al.  Felicity conditions for human skill acquisition: validating an ai-based theory , 1983 .

[4]  John McCarthy,et al.  Circumscription - A Form of Non-Monotonic Reasoning , 1980, Artif. Intell..

[5]  R. Clough.  The Finite Element Method in Plane Stress Analysis , 1960 .

[6]  Sridhar Mahadevan,et al.  Verification-based learning: a generalisation strategy for inferring problem-reduction methods , 1985, IJCAI 1985.

[7]  Edward L. Wilson,et al.  Structural analysis of axisymmetric solids. , 1965 .

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

[9]  Arthur L. Samuel,et al.  Some Studies in Machine Learning Using the Game of Checkers , 1967, IBM J. Res. Dev..

[10]  Marvin Minsky,et al.  Semantic Information Processing , 1968 .

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

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

[13]  Gerald J. Sussman,et al.  Forward Reasoning and Dependency-Directed Backtracking in a System for Computer-Aided Circuit Analysis , 1976, Artif. Intell..

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

[15]  Allen Newell.  The Knowledge Level (Presidential Address) , 1980, AI Mag..

[16]  Ryszard S. Michalski,et al.  Selection of Most Representative Training Examples and Incremental Generation of VL1 Hypotheses: The Underlying Methodology and the Description of Programs ESEL and AQ11 , 1978 .

[17]  John E. Laird,et al.  Current research on learning in Soar , 1986 .

[18]  M. Black.  Models and metaphors , 1962 .

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

[20]  Gerald Jay Sussman,et al.  CONSTRAINTS - A Language for Expressing Almost-Hierarchical Descriptions , 1980, Artif. Intell..

[21]  John McCarthy,et al.  Programs with common sense , 1960 .

[22]  Donald A. Waterman,et al.  Pattern-Directed Inference Systems , 1981, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[23]  H. C. Martin,et al.  Finite Element Analysis of Fluid Flows , 1968 .

[24]  J. Archer.  Consistent matrix formulations for structural analysis using finite-element techniques. , 1965 .

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

[26]  Frederick Hayes-Roth,et al.  An interference matching technique for inducing abstractions , 1978, CACM.

[27]  Thomas Ellman,et al.  Generalizing Logic Circuit Designs by Analyzing Proofs of Correctness , 1985, IJCAI.

[28]  Robert Balzer,et al.  Kestrel Institute: REPORT ON A KNOWLEDGE-BASED SOFTWARE ASSISTANT , 1986 .

[29]  Barr and Feigenbaum Edward A. Avron,et al.  The Handbook of Artificial Intelligence , 1981 .

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

[31]  Tom Michael Mitchell.  Version spaces: an approach to concept learning. , 1979 .

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

[33]  J. Strutt.  V. On the theory of resonance , 1871, Philosophical Transactions of the Royal Society of London.

[34]  Joseph Y. Halpern,et al.  A Guide to the Modal Logics of Knowledge and Belief: Preliminary Draft , 1985, IJCAI.

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

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

[37]  Tom M. Mitchell,et al.  Learning by experimentation: acquiring and refining problem-solving heuristics , 1993 .

[38]  D. V. Hutton,et al.  Modal analysis of a deployable truss using the finite element method , 1984 .

[39]  R. Courant.  Variational methods for the solution of problems of equilibrium and vibrations , 1943 .

[40]  Gerald DeJong,et al.  Learning Schemata for Natural Language Processing , 1985, IJCAI.

[41]  M. Forray,et al.  Variational Calculus in Science and Engineering , 1968 .

[42]  Steve Tappel,et al.  Some Algorithm Design Methods , 1980, AAAI.

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

[44]  Kurt Van Lehn,et al.  Felicity conditions for human skill acquisition: validating an al-based theory , 1983 .

[45]  Robert Balzer,et al.  Report on a knowledge-based software assistant , 1986 .

[46]  Agustin A. Araya,et al.  Learning Problem Classes by Means of Experimentation and Generalization , 1984, AAAI.

[47]  Edward L. Wilson,et al.  Application of the finite element method to heat conduction analysis , 1966 .

[48]  Tom M. Mitchell,et al.  MODEL-DIRECTED LEARNING OF PRODUCTION RULES1 , 1978 .

[49]  Russell Greiner,et al.  What's New? A Semantic Definition of Novelty , 1983, IJCAI.

[50]  Joseph Edward Shigley,et al.  Mechanical engineering design , 1972 .

[51]  Tom M. Mitchell,et al.  Generalization as Search , 2002 .

[52]  S. Vera,et al.  Induction of Concepts in the Predicate Calculus , 1975, IJCAI.

[53]  Ryszard S. Michalski,et al.  On the Quasi-Minimal Solution of the General Covering Problem , 1969 .

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

[55]  John R. Anderson,et al.  MACHINE LEARNING An Artificial Intelligence Approach , 2009 .

[56]  Arthur L. Samuel,et al.  Some studies in machine learning using the game of checkers , 2000, IBM J. Res. Dev..

[57]  John McCarthy,et al.  Applications of Circumscription to Formalizing Common Sense Knowledge , 1987, NMR.

[58]  J. Armstrong.  Knowledge and Belief , 1953 .

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

[60]  F. Beer.  Vector Mechanics for Engineers: Statics and Dynamics , 2003 .

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

[62]  J. Ross Quinlan,et al.  Learning Efficient Classification Procedures and Their Application to Chess End Games , 1983 .

[63]  Joshua Lederberg,et al.  Applications of Artificial Intelligence for Organic Chemistry: The DENDRAL Project , 1980 .

[64]  Stuart J. Russell,et al.  The compleat guide to MRS , 1985 .

[65]  Bruce W. Porter,et al.  Episodic Learning , 1983, AAAI.

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

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

[68]  Thomas G. Dietterich,et al.  Inductive Learning of Structural Descriptions: Evaluation Criteria and Comparative Review of Selected Methods , 1981, Artif. Intell..

[69]  A. Love.  A treatise on the mathematical theory of elasticity , 1892 .

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

[71]  James Arthur Gosling,et al.  Algebraic constraints , 1983 .

[72]  R. Budynas,et al.  Advanced Strength and Applied Stress Analysis , 1977 .

[73]  Pat Langley,et al.  Learning Effective Search Heuristics , 1983, IJCAI.

[74]  Paul E. Utgoff,et al.  Shift of bias for inductive concept learning , 1984 .