More Web Proxy on the site http://driver.im/

article

Free access

Explanation-based learning: a survey of programs and perspectives

Author:

Thomas EllmanAuthors Info & Claims

ACM Computing Surveys (CSUR), Volume 21, Issue 2

Pages 163 - 221

https://doi.org/10.1145/66443.66445

Published: 01 June 1989 Publication History

Abstract

Explanation-based learning (EBL) is a technique by which an intelligent system can learn by observing examples. EBL systems are characterized by the ability to create justified generalizations from single training instances. They are also distinguished by their reliance on background knowledge of the domain under study. Although EBL is usually viewed as a method for performing generalization, it can be viewed in other ways as well. In particular, EBL can be seen as a method that performs four different learning tasks: generalization, chunking, operationalization, and analogy.

This paper provides a general introduction to the field of explanation-based learning. Considerable emphasis is placed on showing how EBL combines the four learning tasks mentioned above. The paper begins with a presentation of an intuitive example of the EBL technique. Subsequently EBL is placed in its historical context and the relation between EBL and other areas of machine learning is described. The major part of this paper is a survey of selected EBL programs, which have been chosen to show how EBL manifests each of the four learning tasks. Attempts to formalize the EBL technique are also briefly discussed. The paper concludes with a discussion of the limitations of EBL and the major open questions in the field.

References

[1]

AHN, W., MOONr~, R. J., BREWER, W. F., AND DEJONG, G. F. 1987. Schema acquisition from one example: Psychological evidence for explanation-based learning. Tech. Rep. UILU- ENG-87-2231, Coordinated Science Laboratory, Univ. of Illinois, Urbana-Champaign, Ill.

[2]

AMAREL, $. 1968. On representations of problems of reasoning about actions. In Machine Intelligence 3, D. Michie, Ed. American Elsevier, New York, pp. 131-171.

[3]

ANDERSON, J. R. 1983a. The Architecture of Cognition. Harvard Univ. Press, Cambridge, Mass.

[4]

ANDERSON, J. R. 1983b. Acquisition of proof skills in geometry. In Machine Learning: An Artificial Intelligence Approach, R. S. Michalski, J. G. Carbonell, and T. M. Mitchell, Eds. Morgan Kaufmann, Los Altos, Calif., pp. 191-219.

[5]

ANDERSON, J. R. 1986. Knowledge compilation: The general learning mechanism, in Machine Learning: An Artificial Intelligence Approach, Volume H, R. S. Michalski, J. G. Carbonell, and T. M. Mitchell, Eds. Morgan Kaufmann, Los Altos, Calif., pp. 289-310.

[6]

ANGLUIN, D., AND SMITH, C. H. 1983. Inductive inference: Theory and methods. A CM Comput. Surv. 15, 3 (Sept.), 237-269.

[7]

BALZER, R. GOLDMAN, N., AND WILE, D. 1976. On the transformational implementation approach to programming. In Proceedings of the 2nd International Conference on Software Engineering. IEEE, New York, pp. 337-343.

[8]

BANERJI, R. B., AND ERNST, C. W. 1972. Strategy construction using homomorphisms between games. Artif. InteU. 3, 223-249.

[9]

BENJAMIN, D. P. 1987. Learning strategies by reasoning about rules. In Proceedings of the l Oth International Joint Conference on Artificial Intelligence. Morgan Kaufmann, Los Altos, Calif., pp. 256-259.

[10]

BENNETT, $. W. 1987. Approximation in mathematical domains. In Proceedings of the l Oth International Joint Conference on Artificial Intelligence. Morgan Kaufmann, Los Altos, Calif., pp. 239-241.

[11]

BERGADANO, r., AND GIORDANA, A. 1988. A knowledge intensive approach to concept induction. In Proceedings of the 5th International Conference on Machine Learning. Morgan Kaufmann, Los Altos, Calif., pp. 305-317.

[12]

BERWlCK, R. C. 1985. The Acquisition of Syntactic Knowledge. MIT Press, Cambridge, Mass.

[13]

BRAVERMAN, M. $., AND RUSSELL, S. J. 1988. Boundaries of operationality. In Proceedings of the 5th International Conference on Machine Learning. Morgan Kaufmann, Los Altos, Calif., pp. 221-234.

[14]

BUCHANAN, $. C., AND MITCHELL, T. M. 1978. Model-directed learning of production rules. In Pattern-Directed Inference Systems, D. A. Waterman and F. Hayes-Roth, Eds. Academic Press, Orlando, Fla., pp. 297-312.

[15]

BYLANDER, V., AND WEINTRAUB, M. A. 1988. A corrective learning procedure using different explanatory types. In Proceedings of the AAAI Spring Symposium on Explanation-Based Learning. AAAI, Menlo Park, Calif., pp. 27-30.

[16]

CARBONELL, J. G. 1983a. Derivational analogy and its role in problem solving. In Proceedings of the National Conference on Artificial Intelligence. Morgan Kaufmann, Los Altos, Calif., pp. 64-69.

[17]

CARBONELL, J. G. 1983b. Learning by analogy: Formulating and generalizing plans from past experience. In Machine Learning: An Artificial Intelligence Approach, R. S. Michalski, J. G. Carbonell, and T. M. Mitchell, Eds. Morgan Kaufmann, Los Altos, Calif., pp. 137-161.

[18]

CARBONELL, J. G. 1986. Derivational analogy: A theory of reconstructive problem solving and expertise acquisition. In Machine Learning: An Artificial Intelligence Approach, Volume H, R. S. Michalski, J. G. Carbonell, and T. M. Mitchell, Eds. Morgan Kaufmann, Los Altos, Calif., pp. 371-392.

[19]

CARBONELL, J. G., AND GIL, Y. 1987. Learning by experimentation. In Proceedings of the 4th International Workshop on Machine Learning. Morgan Kaufmann, Los Altos, Calif., pp. 256-266.

[20]

CARPINETO, C. 1988. An approach based on integrated learning to generating stories from stories. In Proceedings of the 5th International Conference on Machine Learning. Morgan Kaufmann, Los Altos, Calif., pp. 298-304.

[21]

CHENG, P. W., AND CARBONELL, J. G. 1986. The Fermi system: Inducing iterative macro-operators from experience. In Proceedings of the 5th National Conference on Artificial Intelligence. Morgan Kaufmann, Los Altos, Calif., pp. 490-495.

[22]

CHIEN, S. A. 1987a. Extending explanation-based learning: Failure-driven schema refinement. Tech. Rep. UILU-ENG-87-2203, Coordinated Science Laboratory, Univ. of Illinois, Urbana- Champaign, Ill.

[23]

CHIEN, S. A. }987b. Simplifications in temporal persistence: An approach to the intractable domain theory problem in explanation-based learning. Tech. Rep. UILU-ENG-87-2255, Coordinated Science Laboratory, Univ. of Illinois, Urbana- Champaign, Ill.

[24]

CHIEN, $. A. 1988. A framework for explanationbased refinement. In Proceedings of the AAAI Spring Symposium on Explanation-Based Learning. AAAI, Menlo Park, Calif., pp. 137-141.

[25]

CLANCEY, W. J. 1988. Detecting and coping with failure. In Proceedings of the AAAI Spring Symposium on Explanation-Based Learning. AAAI, Menlo Park, Calif., pp. 22-26.

[26]

COHEN, P. R., AND FEIGENBAUM, E. A. (Eds.) 1982. The Handbook of Artificial Intelligence, Volume 3. William Kaufmann, Inc., Los Altos, Calif., pp. 323-511.

[27]

COHEN, W. W. 1988. Generalizing number and learning from multiple examples in explanationbased learning. In Proceedings of the 5th International Conference on Machine Learning. Morgan Kaufmann, Los Altos, Calif., pp. 256-269.

[28]

CULLINGFORD, R. 1978. Script application: Computer understanding of newspaper stories. Tech. Rep. 116, Dept. of Computer Science, Yale Univ., New Haven, Conn.

[29]

DANYLUK, A. P. 1987. The use of explanations for similarity-based learning. In Proceedings of the lOth International Joint Conference on Artificial Intelligence. Morgan Kaufmann, Los Altos, Calif., pp. 274-276.

[30]

DANYLUK, A. P. 1988. Integrated learning is a two way street. In Proceedings of the AAAI Spring Symposium on Explanation-Based Learning. AAAI, Menlo Park, Calif., pp. 36-40.

[31]

DAVIES, T. R., AND RUSSELL, S. J. 1987. A logical approach to reasoning by analogy. In Proceedings of the l Oth International Joint Conference on Artificial Intelligence. Morgan Kaufmann, Los Altos, Calif., pp. 264-270.

[32]

DAVlS, R. 1985. Diagnostic reasoning based on structure and behavior. In Qualitative Reasoning about Physical Systems, D. G. Bobrow, Ed. MIT Press, Cambridge, Mass., pp. 347-410. Also found in Artif InteU. 24.

[33]

DAWSON, C., AND SIKLOSSY, L. 1977. The role of preprocessing in problem solving systems. In Proceedings of the 5th International Joint Conference on Artificial Intelligence. Morgan Kaufmann, Los Altos, Calif., pp. 465-471.

[34]

DEJONG, G. F. 1981. Generalizations based on explanations. In Proceedings of the 7th International Joint Conference on Artificial Intelligence. Morgan Kaufmann, Los Altos, Calif., pp. 67-69.

[35]

DEJONG, G. F. 1986. An approach to }earning from observation. In Machine Learning: An Artificial Intelligence Approach, Volume H, R. S. Michalski, J. G. Carbonell, and T. M. Mitchell, Eds. Morgan Kaufmann, Los Altos, Calif., pp. 571-590.

[36]

DEJONG, G. F., AND MOONEY, R. 1986. Explanationbased learning: An alternative view. Mach. Learn. 1, 2, 145-176.

[37]

DIETTERICH, T. G. 1986. Learning at the knowledge level. Mach. Learn. 1, 3, 287-315.

[38]

DIETTERICH, T. G., AND FLANN, N. S. 1988. An inductive approach to the imperfect theory problem. In Proceedings of the AAAI Spring Symposium on Explanation-Based Learning. AAAI, Menlo Park, Calif., pp. 42-46.

[39]

DIETTERICH, T. G., AND MICHALSKI, R. S. 1981. Inductive learning of structural descriptions: Evaluation criteria and comparative review of selected methods. Artif. Intell. 16, 257-294.

[40]

DIJKSTRA, E. W. 1976. A Discipline of Programming. Prentice-Hall, Englewood Cliffs, N.J.

[41]

DOYLE, J. 1979. A truth maintenance system. Artif. lntell. 12, 231-272.

[42]

DOYLE, R. J. 1986. Constructing and refining causal explanations for an inconsistent domain theory. in Proceedings of the 5th National Conference on Artificial intelligence. Morgan Kaufmann, Los Altos, Calif., pp. 538-544.

[43]

ELLMAN, T. 1985. Generalizing logic circuit designs by analyzing proofs of correctness. In Proceedings of the 9th International Joint Conference on Artificial Intelligence. Morgan Kaufmann, Los Altos, Calif., pp. 643-646.

[44]

ELLMAN, T. 1988. Approximate theory formation: An explanation-based approach. In Proceedings of the 7th National Conference on Artificial Intelligence. Morgan Kaufmann, Los Altos, Calif., pp. 571-574.

[45]

FIKES, R. E., HART, P. E., AND NILSSON, N. J. 1972. Learning and executing generalized robot plans. Artif. Intell. 3, 251-288.

[46]

FLANN, N. S., AND DIETTERICH, T. G. 1986. Selecting appropriate representations for learning from examples. In Proceedings of the 5th National Conference on Artificial Intelligence. Morgan Kaufmann, Los Altos, Calif.

[47]

FORGY, C. L. 1981. OPS5 user's manual. Tech. Rep. CMU-CS-81-135, Dept. of Computer Science. Carnegie-Mellon Univ., Pittsburgh, Pa.

[48]

GENTNER, n. 1983. Structure mapping: A theorelical framework for analogy. Cognitive Sci. 7, 155- ~70.

[49]

GIBSON, W. B. 1974. Hoyle's Modern Encyclopedia of Card Games. Doubleday, Garden City, N.Y.

[50]

GUPTA, A. 1987. Explanation-based failure recovery. In Proceedings of the 6th National Conference on Artificial Intelligence. Morgan Kaufmann, Los Altos, Calif., pp. 606-610.

[51]

GUPTA, A. 1988. Significance of the explanation language in EBL. In Proceedings of the AAAI Spring Symposium on Explanation-Based Learning. AAAI, Menlo Park, Calif., pp. 73-77.

[52]

HALL, R. J. 1988. Learning by failing to explain: Using partial explanations to learn in incomplete or intractable domains. Mach. Learn. 3, 1, 45-77.

[53]

HAMMOND, K. J. 1986. Learning to anticipate and avoid planning problems through the explanat ion of failures. In Proceedings of the 5th National Conference on Artificial Intelligence. Morgan Kaufmann, Los Altos, Calif., pp. 556-560.

[54]

HAMMOND, K. J. 1987. Learning and reusing explanations. In Proceedings of the 4th International Workshop on Machine Learning. Morgan KauL mann, Los Altos, Calif., pp. 141-147.

[55]

HAYES-ROTH, F., AND MOSTOW, D. J. 1981. Machine transformation of advice into a heuristic search procedure. In Cognitive Skills and Their Acquisition, J. R. Anderson, Ed. Erlbaum, Hillsdale, N.J., pp. 231-253.

[56]

HILL, W. L. 1987. Machine learning for software reuse. In Proceedings of the l Oth International Joint Conference on Artificial Intelligence. Morgan Kaufmann, Los Altos, Calif., pp. 338-344.

[57]

HIRSH, H. 1987. Explanation-based generalizalion in a logic programming environment. In Proceedings of the l Oth International Joint Conference on Artificial Intelligence. Morgan Kaufmann, Los Altos, Calif., pp. 221-227.

[58]

HIRSH, H. 1988a. Reasoning about operationality for explanation-based learning. In Proceedings of the 5th International Conference on Machine Learning. Morgan Kaufmann, Los Altos, Calif., pp. 214-220.

[59]

HIRSH, H. 1988b. Empirical techniques for repairing imperfect theories. In Proceedings of the AAAI Spring Symposium on Explanation-Based Learning. AAAI, Menlo Park, Calif., pp. 57-61.

[60]

HUHNS, M. N., AND ACOSTA, R. D. 1987. Argo: An analogical reasoning system for solving design problems. Tech. Rep. AI/CAD-092-87, Microelectronics and Computer Technology Corporation, Austin, Tex.

[61]

HUNTER, L. 1988. Explanation-based discovery. In Proceedings of the AAAI Spring Symposium on Explanation-Based Learning. AAAI, Menlo Park, Calif., pp. 2-7.

[62]

IBA, G. A. 1985. Learning by discovering macros in puzzle solving. In Proceedings of the 9th International Joint Conference on Artificial Intelligence. Morgan Kaufmann, Los Altos, Calif., pp. 640-642.

[63]

KEDAR-CABELLI, $. T. 1985. Purpose-directed analogy. In Proceedings of the 7th Annual Conference of the Cognitive Science Society. Lawrence Carlbaum, Hillsdale, N.J.

[64]

KEDAR-CABELLI, S. T. 1987. Formulating concepts according to purpose. In Proceedings of the 6th National Conference on Artificial Intelligence. Morgan Kaufmann, Los Altos, Calif., pp. 477-481.

[65]

KEDAR-CABELLI, $. T., AND MCCARTY, L. T. 1987. Explanation-based generalization as resolution theorem proving. In Proceedings' of the 4th International Workshop on Machine Learning. Morgan Kaufmann, Los Altos, Calif., pp. 383-389.

[66]

KELLER, R. M. 1983. Learningby re-expressing concepts for efficient recognition. In Proceedings of the National Conference on Artificial Intelligence. Morgan Kaufmann, Los Altos, Calif., pp. 182-186.

[67]

KELLER, R. M. 1987a. The role of explicit contextual knowledge in learning concepts to improve performance. Ph.D. thesis and Tech. Rep. ML- TR-7, Dept. of Computer Science, Rutgers Univ., New Brunswick, N.J.

[68]

KELLER, R. M. 1987b. Concept learning in context. In Proceedings of the 4th International Workshop on Machine Learning. Morgan Kaufmann, Los Altos, Calif., pp. 91-102.

[69]

KELLER, R. M. 1988a. Operationality and generality in explanation-based learning: Separate dimensions or opposite endpoints? In Proceedings of the AAAI Spring Symposium on Explanation- Based Learning. AAAI, Menlo Park, Calif., pp. 153-157.

[70]

KELLER, R. M. 1988b. Defining operationality for explanation-based learning. Artif. InteU. 35, 227-241.

[71]

KORF, R. E. 1985. Macro operators: A weak method for learning. Artif. lnteU. 26, 35-77.

[72]

LAIRD, J. E. 1984. Universal subgoaling. Ph.D. thesis, Dept. of Computer Science, Carnegie-Mellon Univ., Pittsburgh, Pa.

[73]

LAIRD, J. E., AND NEWELL, A. 1983a. A universal weak method: Summary of results. In Proceedings of the 8th International Joint Conference on Artificial Intelligence. Morgan Kaufmann, Los Altos, Calif., pp. 771-773.

[74]

LAIRD, J. E., AND NEWELL, A. 1983b. A universal x3eak method. Tech. Rep. CMU-CS-83-141, Dept. of Computer Science, Carnegie-Mellon Univ., Pittsburgh, Pa.

[75]

LAIRD, J. E., NEWELL, A., AND ROSENBLOOM, P. S. 1987. SOAR: Architecture for general intelligence. Artif. InteU. 33, 1-64.

[76]

LAIRD, J. E., ROSENBLOOM, P. S., AND NEWELL, A. 1984. Towards chunking as a general learning mechanism. In Proceedings of the National Conference on Artificial Intelligence. Morgan Kaufmann, Los Altos, Calif., pp. 188-192.

[77]

LAIRD, J. E., ROSENBLOOM, P. S., AND NEWELL, A. 1986a. Chunking in SOAR: The anatomy of a general learning mechanism. Mach. Learn. 1, 1, 11-46.

[78]

LAIRD, J. E., ROSENBLOOM, P. S., AND NEWELL, A. 1986b. Over-generalization during knowledge compilation in SOAR. In Proceedings of the Workshop on Knowledge Compilation. Department of Computer Science, Oregon State University, Otter Crest, Or., Sept 24-26, pp. 46-57.

[79]

LANGLEY, P. 1986. The terminology of machine learning. Mach. Learn. I, 2, 141-144.

[80]

LEBOWITZ, M. 1983. Generalization from natural language text. Cognitive Sci. 7, 1, 1-40.

[81]

LEBOWITZ, M. 1986a. Integrated learning: Controlling explanation. Cognitive Sci. I0, 2, 219-240.

[82]

LEBOWITZ, M. 1986b. Not the path to perdition: The utility of similarity-based learning. In Proceedings of the 5th National Conference on Artificial Intelligence. Morgan Kaufmann, Los Altos, Calif., pp. 533-537.

[83]

LENAT, D. B. 1982. AM: Discovery in mathematics as heuristic search. In Knowledge-Based Systems in Artificial Intelligence, R. Davis and D. B. Lenat, Eds. McGraw-Hill, New York, pp. 1-225.

[84]

LENAT, D. B., PRAKASH, M., AND SHEPHERD, M. 1986. CYC: Using common sense knowledge to overcome brittleness and knowledge acquisition bottlenecks. AI Mag. 6, 4, 65-85.

[85]

LEWIS, C. H. 1978. Production system models of practice effects. Ph.D. thesis, Computer Science Dept., Univ. of Michigan, Ann Arbor, Mich.

[86]

MAHADEVAN, S. 1985. Verification-based learning: A generalization strategy for inferring problemdecomposition methods. In Proceedings of the 9th International Joint Conference on Artificial Intelligence. Morgan Kaufmann, Los Altos, Calif., pp. 616-623.

[87]

MAHADEVAN, S., AND TADEPALLI, P. 1988. On the tractability of learning from incomplete theories. In Proceedings of the 5th International Conference on Machine Learning. Morgan Kaufmann, Los Altos, Calif., pp. 235-241.

[88]

MANO, M. M. 1976. Computer System Architecture. Prentice-Hall, Englewood Cliffs, N.J.

[89]

MARKOVITCH, S., AND SCOTT, P. D. 1988. The role of forgetting in learning. In Proceedings of the 5th International Conference on Machine Learning. Morgan Kaufmann, Los AItos, Calif., pp. 459-465.

[90]

MCCARTHY, J. 1968. Programs with common sense. In Semantic Information Processing, M. Minsky, Ed. MIT Press, Cambridge, Mass., pp. 403-418.

[91]

MICHALSKI, R. $. 1980. Pattern recognition as ruleguided inductive inference. IEEE Trans. Pattern Anal. Mach. Intell. 2, 4, 349-361.

[92]

MICHALSKI, R. S. 1983. A theory and methodology of inductive learning. Artif. InteU. 20, 111-161.

[93]

MICHALSKI, R. S., CARBONELL, J. G., AND MITCHELL, T. M., Eds. 1983. Machine Learning: An Artificial Intelligence Approach. Morgan Kaufmann, Los Altos, Calif.

[94]

MILLER, G. A. 1956. The magic number seven, plus or minus two: Some limits on our capacity for processing information. Psychol. Rev. 63, 81-97.

[95]

MINTON, S. 1984. Constraint-based generalization: Learning game playing plans from single examples. in Proceedings of the National Conference on Artificial Intelligence. Morgan Kaufmann, Los Altos, Calif., pp. 251-254.

[96]

MINTON, S. 1985. Selectively generalizing plans for problem-solving. In Proceedings of the 9th International Joint Conference on Artificial Intelligence. Morgan Kaufmann, Los Altos, Calif., pp. 596-599.

[97]

MINTON, $. 1988a. Learning effective search control knowledge: An explanation-based approach. Ph.D. thesis and Tech. Rep. CMU-CS-88-133, Dept. of Computer Science, Carnegie-Mellon Univ., Pittsburgh, Pa.

[98]

MINTON, S. 1988b. Quantitative results concerning the utility of explanation-based learning. In Proceedings of the 7th National Conference on Artificial Intelligence. Morgan Kaufmann, Los Altos, Calif., pp. 564-569.

[99]

MINTON, $., AND CARBONELL, J. C. 1987. Strategies for learning search control rules: An explanationbased approach. In Proceedings of the l Oth international Joint Conference on Artificial Intelligence. Morgan Kaufmann, Los Altos, Calif., pp. 228-235.

[100]

MITCHELL, T. U. 1978. Version spaces: An approach to concept learning. Tech. Rep. HPP-79-2, Computer Science Dept., Stanford Univ., Palo Alto, Calif.

[101]

MITCHELL, T. M. 1980. The need for biases in learning generalizations. Tech. Rep. CBM-TR-117, Dept. of Computer Science, Rutgers Univ., New Brunswick, N.J.

[102]

MITCHELL, T. M. 1982a. Generalization as search. Artif. Intell. I8, 203-226.

[103]

MITCHELL, W. M. 1982b. Toward combining empirical and analytical methods for inferring heuristics. Tech. Rep. LCSR-TR-27, Dept. of Computer Science, Rutgers Univ., New Brunswick, N.J.

[104]

MITCHELL, T. M. 1983. Learning and problem solving. In Proceedings of the 8th International Joint Conference on Artificial Intelligence. Morgan Kaufmann, Los Altos, Calif., pp. 1139-1151.

[105]

MITCHELL, T. M., KELLER, R. M., AND KEDAR- CABELLI, S. V. 1986. Explanation-based learning: A unifying view. Mach. Learn. 1, 1, 47-80.

[106]

MITCHELL, T. M., MAHADEVAN, $., AND STEINBERG, L. I. 1985. LEAP: A learning apprentice system for VLSI design, in Proceedings of the 9th International Joint Conference on Artificial Intelligence. Morgan Kaufmann, Los Altos, Calif., pp. 573-580.

[107]

MITCHELL, T. M., UTGOFF, P. E., AND BANERJI, R. 1983a. Learning by experimentation: Acquiring and refining problem-solving heuristics. In Machine Learning: An Artificial Intelligence Approach, R. S. Michalski, J. G. Carbonell, and T. M. Mitchell, Eds. Morgan Kaufmann, Los Altos, Calif., pp. 163-190.

[108]

MITCHELL, T. M., UTGOFF, P. E., NUDEL, B., AND BANERJI, R. 1981. Learning problem solving heuristics through practice. In Proceedings of the 7th International Joint Conference on Artificial Intelligence. Morgan Kaufmann, Los Altos, Calif., pp. 127-134.

[109]

MITCHELL, T. M., et al. 1983b. An intelligent aid for circuit redesign. In Proceedings of the National Conference on Artificial Intelligence. Morgan Kaufmann, Los Altos, Calif., pp. 274-278.

[110]

MOONEY, R. J. 1985. Generalizing explanations of narratives into schemata. M.S. thesis and Tech. Rep. T-159, Coordinated Science Laboratory, Univ. of Illinois, Urbana-Champaign, Ill.

[111]

MOONEY, R. J. 1988. Generalizing the order of operators in macro-operators. In Proceedings of the 5th International Conference on Machine Learning. Morgan Kaufmann, Los Altos, Calif., pp. 270-283.

[112]

MOONEY, R. J., AND BENNETT, $. W. 1986. A domain independent explanation-based generalizer. In Proceedings of the 5th National Conference on Artificial Intelligence. Morgan Kaufmann, Los Altos, Calif., pp. 551-555.

[113]

MOONEY, R., AND DEJONG, G. F. 1985. Learning schemata for natural language processing. In Proceedings of the 9th International Joint Conference on Artificial Intelligence. Morgan Kaufmann, Los Altos, Calif., pp. 681-687.

[114]

MOSTOW, D. J. 1981. Mechanical transformation of task heuristics into operational procedures. Ph.}). thesis and Tech. Rep. CMU-CS-81-113, Dept. of Computer Science, Carnegie-Mellon Univ., Pittsburgh, Pa.

[115]

MOSTOW, D. J. 1983. Machine transformation of advice into a heuristic search procedure. In Machine Learning: An Artificial Intelligence Approach, R. S. Michalski, J. G. Carbonell, and T. M. Mitchell, Eds. Morgan Kaufmann, Los Altos, Calif., 367-403.

[116]

MOSTOW, J. 1983a. Operationalizing advice: A problem-solving model. In Proceedings of the International Workshop on Machine Learning. Dept. of Computer Science, Univ. Illinois, Urbana, Ill., pp. 110-116.

[117]

MOSTOW, J. 1983b. A problem solver for making advice operational. In Proceedings of the National Conference on Artificial Intelligence. Morgan Kaufmann, Los Altos, Calif., pp. 279-283.

[118]

MOSTOW, J. 1986. Why are design derivations hard to replay? In Machine Learning: A Guide to Current Research, T. M. Mitchell, J. G. Carbonell, and R. S. Michalski, Eds. Kluwer, Norwell, Mass.

[119]

MOSTOW, J. 1987a. Design by derivational analogy: Issues in the automated replay of design plans. Tech. Rep. ML-TR-22, Computer Science Dept., Rutgers Univ., New Brunswick, N.J.

[120]

MOSTOW, J. 1987b. Searching for operational concept descriptions in BAR, MetaLEX and EBG. In Proceedings of the 4th International Workshop on Machine Learning. Morgan Kaufmann, Los Altos, Calif., pp. 376-382.

[121]

MOSTOW, J., AND BARLEY, M. 1987. Automated reuse of design plans. Tech. Rep. ML-TR-14, Computer Science Dept., Rutgers Univ., New Brunswick, N.J.

[122]

MOSTOW, J., AND BHATNAGAR, N. 1987. Failsafe-- A floor planner that uses EBG to learn from its failures. In Proceedings of the I Oth International Joint Conference on Artificial Intelligence. Morgan Kaufmann, Los Altos, Calif., pp. 249-255.

[123]

MOSTOW, J., AND COHEN, D. 1985. Automating program speedup by deciding what to cache. In Proceedings of the 9th International Joint Conference on Artificial Intelligence. Morgan Kaufmann, Los Altos, Calif., pp. 165-172.

[124]

MOSTOW, J., AND FAWCETT, T. 1987. Approximating intractable theories: A problem space model. Tech. Rep. ML-TR- 16, Dept. of Computer Science, Rutgers Univ., New Brunswick, N.J.

[125]

NATARAJAN, B. K., AND TADEPALLI, P. 1988. Two new frameworks for learning. In Proceedings of the 5th International Conference on Machine Learning. Morgan Kaufmann, Los Altos, Calif., pp. 402-415.

[126]

NEVES, D. M., AND ANDERSON, J. R. 1981. Knowledge compilation: Mechanisms for the automatization of cognitive skills. In Cognitive Skills and Their Acquisition, J. R. Anderson, Ed. Erlbaum, Hillsdale, N.J.

[127]

NEWrLL, A. 1969. Heuristic programming: Illstructured problems. In Progress in Operations Research, III, J. Aronofsky, Ed. Wiley, New York.

[128]

NEWELL, A. 1980. Reasoning, problem solving, and decision processes: The problem space as a fundamental category. In Attention and Performance VIII, R. Nickerson, Ed. Erlbaum, Hillsdale, N.J.

[129]

NILSSON, N. J. 1980. Principles of Artificial Intelligence. Tioga Publ., Palo Alto, Calif.

[130]

O'RORKE, P. 1984. Generalization for explanationbased schema acquisition. In Proceedings of the National Conference on Artificial Intelligence. Morgan Kaufmann, Los Altos, Calif., pp. 260-263.

[131]

O'RORKE, P. 1986. Recent progress on the mathematician's apprentice project. In Machine Learning: A Guide to Current Research, T. M. Mitchell, J. G. Carbonell, and R. S. Michalski, Eds. Kluwer, Nowell, Mass.

[132]

O'RORKE, P. 1987. LT revisited: Experimental results of applying explanation-based learning to the logic of the Principia Mathematica. In Proceedings of the 4th International Workshop on Machine Learning. Morgan Kaufmann, Los Altos, Calif., pp. 148-159.

[133]

PARTSCH, H.,ANDSTEINBROGGEN, R. 1983. Program transformation systems. ACM Comput. Surv. 15, 3 (Sept.).

[134]

PAZZANI, M. J. 1988. Integrated learning with incorrect and incomplete theories. In Proceedings of the 5th International Conference on Machine Learning. Morgan Kaufmann, Los Altos, Calif., pp. 291-297.

[135]

PAZZANI, M. J., DYER, M., AND FLOWERS, M. 1986. The role of prior causal theories in generalization. In Proceedings of the 5th National Conference on Artificial Intelligence. Morgan Kaufmann, Los Altos, Calif., pp. 545-550.

[136]

PORTER, B. W., AND KIBLER, D. F. 1985. A comparison of analytic and experimental goal regression for machine learning. In Proceedings of the 9th International Joint Conference on Artificial Intelligence. Morgan Kaufmann, Los Altos, Calif., pp. 555-559.

[137]

PORTER, B. W., AND KIBLER, D. F. 1986. Experimental goal regression: A method for learning problem solving heuristics. Mach. Learn. I, 3, 249-285.

[138]

PRIEDITIS, A. E. 1986. Discovery of algorithms from weak methods. In Proceedings of the International Meeting on Advances in Learning (July), Les Arc, France.

[139]

PRIEDITIS, A. E. 1988a. Environment-guided program transformation. In Proceedings of the AAAI Spring Symposium on Explanation-Based Learning. AAAI, Menlo Park, Calif., pp. 201-209.

[140]

PRIEDITIS, A. E., Ed. 1988b. AnaIogica. Morgan Kaufmann, Los Altos, Calif.

[141]

PRIEDITIS, A. E., AND MOSTOW, J. 1987. PROLEARN: Towards a Prolog interpreter that learns. In Proceedings of the 6th National Conference on Artificial Intelligence. Morgan Kaufmann, Los Altos, Calif., pp. 494-498.

[142]

RAJAMONEY, S. A. 1988. Experimentation-based theory revision. In Proceedings of the AAAI Spring Symposium on Explanation-Based Learning. AAAI, Menlo Park, Calif., pp. 7-110.

[143]

RAJAMONEY, S. A., ANn DEJONG, G. F. 1987. The classification, detection and handling of imperfect theory problems. In Proceedings of the l Oth International Joint Conference on Artificial Intelligence. Morgan Kaufmann, Los Altos, Calif., pp. 205-207.

[144]

RAJAMONEY, S. A., AND DEJONG, G. F. 1988. Active explanation reduction: An approach to the multiple explanations problem. In Proceedings of the 5th International Conference on Machine Learning. Morgan Kaufmann, Los Altos, Calif., pp. 242-255.

[145]

RIESBECK, C. K. 1983. Knowledge reorganization and reasoning style. Tech. Rep. YALEU/DCS/ RR#270, Dept. of Computer Science, Yale Univ., New Haven, Conn.

[146]

ROSENBLOOM, P. S. 1983. The chunking of goal hierarchies: A model of practice and stimulusresponse compatibility. Ph.D. thesis and Tech. Rep. CMU-TR-83-148, Dept. of Computer Science, Carnegie-Mellon Univ., Pittsburgh, Pa.

[147]

ROSENBLOOM, P. S., AND LAIRD, J. E. 1986. Mapping explanation-based generalization onto SOAR. In Proceedings of the 5th National Conference on Artificial Intelligence. Morgan Kaufmann, Los Altos, Calif., pp. 561-567.

[148]

ROSENBLOOM, P. S., AND NEWELL, A. 1986. The chunking of goal hierarchies: A generalized model of practice. In Machine Learning: An Artificial Intelligence Approach, Volume II, R. S. Michalski, J. G. Carbonell, and T. M. Mitchell, Eds. Morgan Kaufmann, Los Altos, Calif., pp. 247-288.

[149]

RoY, S., AND MOSTOW, J. 1988. Parsing to learn fine grained rules. In Proceedings of the 7th National Conference on Artificial Intelligence. Morgan Kaufmann, Los Altos, Calif., pp. 547-551.

[150]

RUSSELL, S. J. 1986. Preliminary steps toward the automation of induction. In Proceedings of the 5th National Conference on Artificial Intelligence. Morgan Kaufmann, Los Altos, Calif., pp. 477-484.

[151]

RUSSELL, S. J. 1988. Tree-structured bias. In Proceedings of the 7th National Conference on Artificial Intelligence. Morgan Kaufmann, Los Altos, Calif., pp. 641-645.

[152]

RUSSELL, S. J., AND GROSOF, B. N. 1987. A declarative approach to bias in concept learning. In Proceedings of the 6th National Conference on Artificial Intelligence. Morgan Kaufmann, Los Altos, Calif., pp. 505-510.

[153]

SALZBERG, S. 1983. Generating hypotheses to explain prediction failures. In Proceedings of the National Conference on Artificial Intelligence. Morgan Kaufmann, Los Altos, Calif., pp. 352-355.

[154]

SCHANK, R. C. 1982. Dynamic Memory: A Theory of Reminding and Learning in Computers and People. Cambridge Univ. Press, Cambridge, U.K.

[155]

SCHANK, R. C. 1987. Explanation Patterns. Cambridge Univ. Press, Cambridge, U.K.

[156]

SCHANK, R. C., AND ABELSON, R. P. 1977. Scripts, Plans, Goals and Understanding.' An Inquiry into Human Knowledge Structures. Erlbaum, Hillsdale, N.j.

[157]

SEGRE, A. M. 1986. Explanation-based manipulator learning. In Machine Learning: A Guide to Current Research, T. M. Mitchell, J. G. Carbonell, and R. S. Michalski, Eds. Kluwer, Norwell, Mass.

[158]

SEGRE, A. M. 1987. On the operationality/generality trade-off in explanation-based learning. In Proceedings of the l Oth International Joint Conference on Artificial intelligence. Morgan Kaufmann, Los Altos, Calif., pp. 242-248.

[159]

SEGRE, A. M. 1988. Operationality and real world plans. In Proceedings of the AAAI Spring Symposium on Explanation-Based Learning. AAAI, Menlo Park, Calif., pp. 158-163.

[160]

SEGRE, A. M., AND DEJONG, G. F. 1985. Explanation-based manipulator learning: Acquisition of planning ability through observation. In Proceedings of the IEEE International Conference on Robotics and Automation. IEEE, New York, pp. 555-560.

[161]

SHAVLIK, J. W. 1985. Learning about momentum conservation. In Proceedings of the 9th International Joint Conference on Artificial Intelligence. Morgan Kaufmann, Los Altos, Calif., pp. 667-669.

[162]

SHAVLIK, J. W. 1986. Learning classical physics. In Machine Learning: A Guide to Current Research, T. M. Mitchell, J. G. Carbonell, and R. S. Michalski, Eds. Kluwer, Norwell, Mass.

[163]

SHAVLIK, J. W., ANn DEJONG, G. F. 1987a. An explanation-based approach to generalizing number. In Proceedings of the I Oth International Joint Conference on Artificial Intelligence. Morgan Kaufmann, Los Altos, Calif., pp. 236-238.

[164]

SHAVLIK, J. W., AND DEJONG, G. F. 1987b. BAGGER: An EBL system that extends and generalizes explanations. In Proceedings of the 6th National Conference on Artificial Intelligence. Morgan Kaufmann, Los Altos, Calif., pp. 516-520.

[165]

SHAVLIK, J. W., AND DEJONG, G. F. 1987c. Acquiring special case schemata in explanati(mbased learning. In Proceedings of the 9th Annual Conference of the Cognitive Science Society (July), Seattle, Wash., pp. 851-860.

[166]

SILVER, B. 1986a. Precondition analysis: Learning control information. In Machine Learning.' An Artificial Intelligence Approach, R. S. Michalski, J. G. Carbonell, and T. M. Mitchell, Eds. Morgan Kaufmann, Los Altos, Calif., pp. 647-670.

[167]

SILVER, B. 1986b. Learning control information. In Machine Learning: A Guide to Current Research, T. M. Mitchell, J. G. Carbonell, and R. S. Michalski, Eds. Kluwer, Norwell, Mass.

[168]

SILVER, B. 1988. A hybrid approach in an imperfect domain. In Proceedings of the AAAI Spring Symposium on Explanation-Based Learning. AAAI, Menlo Park, Calif., pp. 52-56.

[169]

SLEEMAN, D., HIRSH, H., AND KIM, I. 1987. Expanding an incomplete domain theory: Two case studies. Tech. Rep. AUCS-TR8704, Univ. of Aberdeen, Aberdeen, Scotland.

[170]

SMITH, R. G., WINSTON, H. A., MITCHELL, V. M., AND BUCHANAN, B. G. 1985. Representation and use of explicit justifications for knowledge base refinement. In Proceedings of the 9th International Joint Conference on Artificial Intelligence. Morgan Kaufmann, Los Altos, Calif., 673-680.

[171]

SOLOWAY, E. M. 1978. Learning - Interpretation + Generalization: A case study in knowledgedirected learning. Ph.D. thesis and Tech. Rep. COINS-TR-78-13, Computer and informati(m Science Dept., Univ. of Massachusetts, Amherst, Mass.

[172]

STALLMAN, R. M., AND SUSSMAN, G. J. 1977. Forward reasoning and dependency-directed backtracking in a system for computer-aided circuit analysis. Artif. InteU. 9, 135-196.

[173]

STEINBERG, L. I., AND MITCHELL, T. M. 1985. The redesign system: A knowledge-based approach to VLSI CAD. IEEE Des. Test Comput. 2, 1, 45-54.

[174]

STEPP, R. E., AND MICHALSKI, R. S. 1986. Conceptual clustering: Inventing goal oriented classifications of structured objects. In Machine Learning: An Artificial Intelligence Approach, Volume H, R. S. Micbalski, J. G. Carbonell, and T. M. Mitchell, Eds. Morgan Kaufmann, Los Altos, Calif., pp. 471-498.

[175]

SUBRAMANIAN, D., AND SMITH, D. 1988. Knowledge level learning: An alternative view. in Proceedings of the AAAI Spring Symposium on Explanation- Based Learning. AAAI, Menlo Park, Calif., pp. 196-200.

[176]

SUSSMAN, G. J. 1975. A Computer Model o{ Skill Acquisition. American Elsevier, New York.

[177]

SWAMINATHAN, K. 1988. Integrated learning with an incomplete and intractable domain theory: The problem of epidemiological diagnosis. In Proceedings of the AAAI Spring Symposium on Explanation-Based Learning. AAAI, Menlo Park, Calif.

[178]

SWARTOUT, W. R. 1983. XPLAIN: A system for creating and explaining expert consulting programs. Artif. Intell. 21, 285-325.

[179]

TADEPALLI, P. V. 1986. Learning approximate plans in games. Tech. Rep. ML-TR-8, Computer Science Dept., Rutgers Univ., New Brunswick, N.J.

[180]

TAMBE, M., AND NEWELL, A. 1988. Some chunks are expensive. In Proceedings of the 5th International Conference on Machine Learning. Morgan Kaufmann, Los Altos, Calif., pp. 451-458.

[181]

UTGorr, P. E. 1986. Shift of bias for inductive concept learning. In Machine Learning: An Artificial Intelligence Approach, Volume//, R. S. Michalski, J. G. Carbonell, and T. M. Mitchell, Eds. Morgan Kaufmann, Los Altos, Calif., pp. 107-148.

[182]

UTGOFF, P. E., AND MITCHELL, T. M. 1982. Acquisition of appropriate bias for inductive concept learning. In Proceedings of the National Conference on Artificial Intelligence. Morgan Kaufmann, Los Altos, Calif., pp. 414-417.

[183]

Van Harmelen, F., and Bundy, A. 1988. Explanationbased generalization--partial evaluation. A rtif. InteU. 36, 401-412.

[184]

VANLEHN, K. 1987. Learning one subprocedure per lesson. Artif. InteU. 3I, 1-40.

[185]

VERr, S. A. 1977. Induction of relational productions in the presence of background information. In Proceedings of the 5th International Joint Conference on Artificial Intelligence. Morgan Kaufmann, Los Altos, Calif., pp. 349-355.

[186]

WALDINGER, R. 1977. Achieving several goals simultaneously. In Machine Intelligence 8, E. Elcock and D. Michie, Eds. Ellis Horwood, London.

[187]

WiLENSKY, R. 1978. Understanding goal-based stories. Tech. Rep. 140, Dept. of Computer Science, Yale Univ., New Haven, Conn.

[188]

WILKINS, D. C. 1988. Knowledge base refinement using apprenticeship learning techniques. In Proceedings of the 7th National Conference on Artificial Intelligence. Morgan Kaufmann, Los Altos, Calif., pp. 646-651.

[189]

WINSTON, P. H. 1972. Learning structural descriptions from examples. In The Psychology of Computer Vision, P. H. Winston, Ed. McGraw-Hill, New York.

[190]

WINSTON, P. $. 1982. Learning new principles from precedents and exercises. Artif. Intell. 19, 321-350.

[191]

WINSTON, P. H., BINFORD, T. O., KATZ, B., AND LOWRY, M. 1983. Learning physical descriptions from functional definitions, examples, and precedents. In Proceedings of the National Conference on Artificial Intelligence. Morgan Kaufmann, Los Altos, Calif., pp. 433-439.

[192]

ZWEBEN, M., AND CHASE, U. P. 1988. Improving operationality with approximate heuristics. In Proceedings of the AAAI Spring Symposium on Explanation-Based Learning. AAAI, Menlo Park, Calif., pp. 100-106.

Cited By

Schneider JVlachos M(2024)Reflective-net: learning from explanationsData Mining and Knowledge Discovery10.1007/s10618-023-00920-038:5(2975-2996)Online publication date: 1-Sep-2024
https://dl.acm.org/doi/10.1007/s10618-023-00920-0
Gupta RGoel S(2022)An Early Predictive and Recovery Mechanism for Scheduled Outages in Service-Based Systems (SBS)International Journal of Software Innovation10.4018/IJSI.30701610:1(1-35)Online publication date: 5-Aug-2022
https://dl.acm.org/doi/10.4018/IJSI.307016
Belkhir ABouyakoub S(2022)Things-NetInternational Journal of Software Innovation10.4018/IJSI.29798110:1(1-27)Online publication date: 6-May-2022
https://dl.acm.org/doi/10.4018/IJSI.297981
Show More Cited By

Recommendations

Explanation-Based Learning and Reinforcement Learning: A Unified View

In speedup-learning problems, where full descriptions of operators are known, both explanation-based learning (EBL) and reinforcement learning (RL) methods can be applied. This paper shows that both methods involve fundamentally the same process of ...
Explanation-Based Neural Network Learning: A Lifelong Learning Approach
Explanation-Based Learning: An Alternative View

In the last issue of this journal Mitchell, Keller, and Kedar-Cabelli presented a unifying framework for the explanation-based approach to machine learning. While it works well for a number of systems, the framework does not adequately capture certain ...

Comments

Please enable JavaScript to view thecomments powered by Disqus.

Information & Contributors

Information

Published In

cover image ACM Computing Surveys

ACM Computing Surveys Volume 21, Issue 2

Jun. 1989

112 pages

ISSN:0360-0300

EISSN:1557-7341

DOI:10.1145/66443

Issue’s Table of Contents

Copyright © 1989 ACM.

Publisher

Association for Computing Machinery

New York, NY, United States

Publication History

Published: 01 June 1989

Published in CSUR Volume 21, Issue 2

Permissions

Request permissions for this article.

Request Permissions

Check for updates

Qualifiers

Article

Contributors

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

107
Total Citations
View Citations
2,220
Total Downloads

Downloads (Last 12 months)163
Downloads (Last 6 weeks)31

Reflects downloads up to 22 Jan 2025

Other Metrics

View Author Metrics

Citations

Cited By

Schneider JVlachos M(2024)Reflective-net: learning from explanationsData Mining and Knowledge Discovery10.1007/s10618-023-00920-038:5(2975-2996)Online publication date: 1-Sep-2024
https://dl.acm.org/doi/10.1007/s10618-023-00920-0
Gupta RGoel S(2022)An Early Predictive and Recovery Mechanism for Scheduled Outages in Service-Based Systems (SBS)International Journal of Software Innovation10.4018/IJSI.30701610:1(1-35)Online publication date: 5-Aug-2022
https://dl.acm.org/doi/10.4018/IJSI.307016
Belkhir ABouyakoub S(2022)Things-NetInternational Journal of Software Innovation10.4018/IJSI.29798110:1(1-27)Online publication date: 6-May-2022
https://dl.acm.org/doi/10.4018/IJSI.297981
Garg RTiwari A(2022)Orrs Orchestration of a Resource Reservation System Using Fuzzy Theory in High-Performance ComputingInternational Journal of Software Innovation10.4018/IJSI.29792310:1(1-28)Online publication date: 6-May-2022
https://dl.acm.org/doi/10.4018/IJSI.297923
Jain TMasand AChauhan S(2022)Depression Identification Through Tweet ClustersInternational Journal of Software Innovation10.4018/IJSI.29791610:1(1-14)Online publication date: 8-Apr-2022
https://dl.acm.org/doi/10.4018/IJSI.297916
Ankali SParthiban L(2022)Accurate and Language Agnostic Code Clone Detection by Measuring Edit Distance of ANTLR Parse TreeInternational Journal of Software Innovation10.4018/IJSI.29791510:1(1-22)Online publication date: 6-May-2022
https://dl.acm.org/doi/10.4018/IJSI.297915
Saadi AHammal YOussalah M(2022)Automata-Based Approach to Manage Self-Adaptive Component-Based ArchitecturesInternational Journal of Software Innovation10.4018/IJSI.29762310:1(1-22)Online publication date: 8-Apr-2022
https://dl.acm.org/doi/10.4018/IJSI.297623
Hassan SBaabad AZulzalil HBaharom S(2022)A Survey on Characterizing the Empirical Analysis, Proposed Approaches, and Research Trends for Architectural DecayInternational Journal of Software Innovation10.4018/IJSI.29751210:1(1-18)Online publication date: 18-Mar-2022
https://dl.acm.org/doi/10.4018/IJSI.297512
Asthana APradhan P(2022)Dynamic Butterfly ACM for Risk Optimization on the Real-Time Unix Operating SystemInternational Journal of Software Innovation10.4018/IJSI.29750510:1(1-16)Online publication date: 1-Apr-2022
https://dl.acm.org/doi/10.4018/IJSI.297505
Singh RBindal AKumar A(2022)Improving Software Design by Mitigating Code SmellsInternational Journal of Software Innovation10.4018/IJSI.29750310:1(1-21)Online publication date: 1-Apr-2022
https://dl.acm.org/doi/10.4018/IJSI.297503
Show More Cited By

View Options

View options

PDF

View or Download as a PDF file.

eReader

View online with eReader.

Login options

Check if you have access through your login credentials or your institution to get full access on this article.

Full Access

Get this Article

Media

Figures

Other

Tables

View Issue’s Table of Contents