Abstract
This paper summarizes progress towards the construction of autonomous learning agents, in particular those that use existing knowledge in the pursuit of new learning goals. To this end, we show that the bias driving a concept-learning program can be expressed as a first-order sentence that reflects knowledge of the domain in question. We then show how the process of learning a concept from examples can be implemented as a derivation of the appropriate bias for the goal concept, followed by a first-order deduction from the bias and the facts describing the instances. Given sufficient back-ground knowledge, the example complexity of learning can be considerably reduced. Shift of bias, certainkinds of “preference-type” bias, and noisy instance data can be handled by moving to a non-monotonic inference system [Grosof & Russell, this volume]. We emphasize that learning can and should be viewed as an interaction between new experiences and existing knowledge.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Angluin, D. and Smith, C. H., (1983) “Inductive Inference: Theory and Methods”. In Computing Surveys, Vol. 15, No. 3, September 1983, pp. 237–269.
Blum, L. and Blum, M., (1975) “Toward a Mathematical Theory of Inductive Inference.” In Information and Control, Vol. 28, pp. 125–55,1975.
Branner, J.S.,Goodnow, J.J. and Austm, G.A.(1956)Astudy of Thinking, New York: 1956.
Buchanan, B. G. and Mitchell, T. M. (1978) “Model-directed Learning of Production Rules”. In Waterman, D. A. and Hayes-Roth, F., (Eds.) Pattern-directed Inference Systems. New York: Academic Press, 1978.
Bundy, A., Silver, B. and Plummer, D., (1985) “An Analytical Comparison of Some Rule-Learning Programs”. In AI Journal, Vol. 27, 1985.
Buntine, W., (1986) “Generalized Subsumption and its Application to Induction and Redundancy”. In Proceedings of ECAI-86, Brighton, UK, 1986.
Charniak, E. and McDermott, D., (1985) Introduction to Artificial Intelligence. Reading, MA: Addison-Wesley.
Davies, T. R., (1985) “Analogy”. Informal Note CSLI-IN-85-4, CSLI, Stanford, 1985.
Davies, T. R. and Russell, Stuart J., (1987) “A Logical Approach to Reasoning by Analogy”. In Proceedings of IJCAI-87, Milan, Italy, 1987.
Dietterich, T. G., (1986) “Learning at the Knowledge Level”. In Machine Learning, Vol. 1, No. 3,1986.
Genesereth, M. R., (1983) “An Overview of Meta-Level Architecture”. In Proceedings of AAAI-83, pp. 119–124,1983.
Gold, E. M., (1967) “Language Identification in the Limit.” In Information and Control, Vol. 10, pp. 447–74,1967.
Goodman, N., (1955) Fact, Fiction and Forecast. Harvard University Press, Cambridge, MA, 1955.
Grosof, B. N. and Russell, S. J., (this volume) “Shift of Bias As Non-Monotonic Reasoning”. In this volume.
Grosof, B. N., (forthcoming) Non-monotonie Theories: Structure, Inference, and Applications (working title). Ph. D. thesis (in preparation), Stanford University, 1989?.
Hirsh, H., (1987) “Explanation-based Generalization in a Logic Programming Environment.” In Proceedings of IJCAI-87, Milan, Italy, 1987.
Keller, R. M., (1987) “Defining Operationally for Explanation-based Learning.” In Proceedings of AAAI-87, Seattle, WA, 1987.
Lenat, D. B., (1983) “Theory Formation by Heuristic Search: the Nature of Heuristics II: Background and Examples.” In Artificial Intelligence, Vol. 21, pp. 31–59,1983.
Mahadevan, S. and Tadepalli, P., (1988) “On the Tractability of Learning from Incomplete Theories”. In Proc. Fifth Intil Conf. on Machine Learning Morgan Kaufman: Ann Arbor, MI.
Michalski, R. S., (1983) “A Theory and Methodology of Inductive Learning.” In Artificial Intelligence, Vol. 20, No. 2,1983.
Mill, J. S.,System of Logic (first published 1843). BookfflCh XX ‘Of Analogy’ in Vol. VIII of Collected Works of John Stuart Mill University of Toronto Press, 1973.
Mitchell, T. M., (1978) Version Spaces: An Approach to Concept Learning. Ph.D. thesis, Stanford University, 1978.
Mitchell, T. M., (1980) “The Need for Biases in Learning Generalizations”. Rutgers University TR CBM-TR-117,1980.
Mitchell, T. M., (1982) “Generalization as Search”. In Artificial Intelligence, Vol. 18, No. 2, pp. 203–226, March 1982.
Mitchell, T. M., Utgoff, P. and Banerji, R., (1983) “Learning by Experimentation: Acquiring and Refining Problem-Solving Heuristics”. In Carbonell, J. G., Michalski, R. and Mitchell T., (eds.) Machine Learning: an Artificial Intelligence Approach. Palo Alto, CA: Tioga Press., 1983.
Mitchell, T. M., Keller, R. M., & Kedar-Cabelli, S. T., (1986). “Explanation-based Generalization: A Unifying View”. Machine Learning, Vol. 1, pp. 47–80,1986.
Mitchell, T. M., (1988). “Can an Autonomous Robot Learn”.Paper presented at the Worshop on Representation and Learning in Autonomous Agents, Lagos, Portugal, Nov. 1988.
Muggleton, S. and Buntine, W., (1988) “Machine Invention of First-order Predicates by Inverting Resolution”. In Proceedings of the Fifth International Machine Learning Conference, Ann Arbor, MI: Morgan Kaufman, 339–352,1988.
Plotkin, G. D., (1970) “A Note on Inductive Generalization.” In Meltzer, B. and Michie, D. (Eds.), Machine Intelligence 5. New York: Elsevier, 1970.
Putnam, H. (1975) “Probability and Confirmation.” In Mathematics, Matter and Method. Cambridge: Cambridge University Press, 1975.
Quinlan, J. R., (1983) “Learning Efficient Classification Procedures and their Application to Chess End Games”. In Carbonell, J. G., Michalski, R. and Mitchell, T., (Eds.) Machine Learning: an Artificial Intelligence Approach. Palo Alto, CA: Tioga Press., 1983.
Rendali, L., (1986) “A General Framework for Induction and a Study of Selective Induction”. Machine Learning, 1, 1986.
Russell, S. J., (1985) The Compleat Guide to MRS. Technical Report No. STAN-CS-85-1080, Stanford University, 1985.
Russell, S. J., (1986a) “Preliminary Steps Toward the Automation of Induction.” In Proceedings of AAAI-86, Philadelphia, PA, 1986.
Russell, S. J., (1986b) Analogical and Inductive Reasoning. Ph.D. thesis, Stanford University, Dec. 1986.
Russell, S. J., and Grosof, B. N., (1987) “A Declaiative Approach to Bias in Concept Leammg”In Proceedings of AAAI-87, pp. 505-10, Seattle, WA, 1987. The first and second halves are complementary but distinct papers. The second half is a preliminary version of (Grosof & Russell, this volume).
Russell, S.J. and Subramanian, D., (this volume) “Mutual Constraints on Representation and Inference.” In this volume.
Russell, S. J., (1988) “Tree-Structured Bias.” In Proceedings AAAI-88, St. Paul, MI, pp. 641-5, 1988.
Russell, S. J., (forthcoming) Knowledge-guided, Autonomous Learning. To appear.
Schlimmer, J. C., (1987) “Incremental Adjustment of Representations for Learning.” In Proceddings of the Fourth International Workshop on Machine Learning. University of California, Irvine, CA: Morgan Kaufman, June, 1987.
Shapiro, E. Y. (1981) “Inductive Inference of Theories from Facts.” Technical Report 192, Department of Computer Science, Yale University, New Haven, CT, 1981.
Simon, H. A. and Lea, G. (1974) “Problem Solving and Rule Induction: A Unified View.” In Knowledge and Cognition, L. W. Gregg (Ed.). Hillsdale, NJ: Erlbaum, 1974.
Subramanian, D. and Feigenbaum, J., (1986) “Factorization in Experiment Generation”. In Proceedings of AAAI-86, pp. 518–522, 1986.
Ullman, J. D., (1983) Principles of Database Systems. Computer Science Press, 1983.
Utgoff, P. E., (1984) Shift of Bias for Inductive Concept Learning. Ph.D. thesis, Rutgers University, 1984.
Watanabe, S., (1969) Knowing and Guessing: A Formaland Quantitative Study. New York, NY: Wiley, 1969.
Winston, P., (1970) Learning StructuredDescriptons from Examples. Ph.D. thesis, Massachusetts Institute of Technology, Cambridge, MA, 1970.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 1990 Kluwer Academic Publishers
About this chapter
Cite this chapter
Russell, S.J., Grosof, B.N. (1990). A Sketch of Autonomous Learning using Declarative Bias. In: Brazdil, P.B., Konolige, K. (eds) Machine Learning, Meta-Reasoning and Logics. The Kluwer International Series in Engineering and Computer Science, vol 82. Springer, Boston, MA. https://doi.org/10.1007/978-1-4613-1641-1_2
Download citation
DOI: https://doi.org/10.1007/978-1-4613-1641-1_2
Publisher Name: Springer, Boston, MA
Print ISBN: 978-1-4612-8906-7
Online ISBN: 978-1-4613-1641-1
eBook Packages: Springer Book Archive