Abstract
The Learning to Reason framework combines the study of Learning and Reasoning into a single task. Within it, learning is done specifically for the purpose of reasoning with the learned knowledge. Computational considerations show that this is a useful paradigm; in some cases learning and reasoning problems that are intractable when studied separately become tractable when performed as a task of Learning to Reason.
In this paper we study Learning to Reason problems where the interaction with the world supplies the learner only partial information in the form of partial assignments. Several natural interpretations of partial assignments are considered and learning and reasoning algorithms using these are developed. The results presented exhibit a tradeoff between learnability, the strength of the oracles used in the interface, and the range of reasoning queries the learner is guaranteed to answer correctly.
Article PDF
Similar content being viewed by others
Explore related subjects
Discover the latest articles, news and stories from top researchers in related subjects.Avoid common mistakes on your manuscript.
References
Angluin, D. (1988). Queries and concept learning. Machine Learning; 2(4), 319–342.
Ben-David, S., & Dichterman, E. (1993). Learning with restricted focus of attention. Proceedings of the Annual ACM Workshop on Computational Learning Theory (pp. 287–296). New York, NY: ACM Press.
Blum, A. (1992). Learning Boolean functions in an infinite attribute space. Machine Learning, 9(4), 373–386.
Blum, A., Hellerstein, L., & Littlestone, N. (1991). Learning in the presence of finitely or infinitely many irrelevant attribute. Proceedings of the Annual ACM Workshop on Computational Learning Theory (pp. 155–166).
Bshouty, N.H. (1995). Exact learning via the monotone theory. Information and Computation, 123(1), 146–153.
Cook, S.A. (1971). The complexity of theorem proving procedures. 3rd Annual ACM Symposium of the Theory of Computing (pp. 151–158). Shaker Heights, OH: ACM Press.
De Raedt, L. (1997). Logical settings for concept learning. Artificial Intelligence, 95(1), 187–201, see also relevant errata (forthcoming).
Frazier, M., & Pitt, L. (1993). Learning from entailment: An application to propositional Horn sentences. Proceedings of the International Conference on Machine Learning (pp. 120–127). Morgan Kaufmann.
Greiner, R., Grove, A., & Kogan, A. (1996). Exploiting the omission of irrelevant data. Proceedings of the International Conference on Machine Learning (pp. 216–224).
Greiner, R., Grove, A., & Roth, D. (1996). Learning active classifiers. Proceedings of the International Conference on Machine Learning (pp. 207–215).
Greiner, R., & Schuurmans, D. (1992). Learning useful Horn approximations. Proceedings of the International Conference on the Principles of Knowledge Representation and Reasoning (pp. 383–392).
Kautz, H., Kearns, M., & Selman, B. (1995). Horn approximations of empirical data. Artificial Intelligence, 74, 129–145.
Kearns, M.J., & Valiant, L.G. (1994). Cryptographic limitations on learning Boolean formulae and finite automata. Journal of the ACM, 41(1), 67–95.
Khardon, R. (1996). Learning to take actions. Proceedings of the National Conference on Artificial Intelligence (pp. 787–792). Portland, OR: AAAI Press.
Khardon, R. (1998). Learning first order universal Horn expressions. Proceedings of the Conference on Computational Learning Theory (pp. 154–165). Madison, Wisconsin: ACM Press.
Khardon, R., & Roth, D. (1996). Reasoning with models. Artificial Intelligence, 87, 187–213.
Khardon, R., & Roth, D. (1997a). Default and relevance in model based reasoning. Artificial Intelligence, 97(12), 169–193.
Khardon, R., & Roth, D. (1997b). Learning to reason. Journal of the ACM, 44(5), 697–725.
Littlestone, N. (1988). Learning quickly when irrelevant attributes abound: A new linear-threshold algorithm. Machine Learning, 2, 285–318.
Moses, Y., & Tennenholtz, M. (1996). Off-line reasoning for on-line efficiency: Knowledge bases. Artificial Intelligence, 83(2), 229–239.
Muggleton, S., & De Raedt, L. (1994). Inductive logic programming: Theory and methods. Journal of Logic Programming, 20, 629–679.
Naor, J., & Naor, M. (1993). Small-bias probability spaces: Efficient constructions and applications. SIAM Journal on Computing, 22(4), 838–856.
Reiter, R. (1987). Nonmonotonic reasoning. Annual Reviews of Computer Science (pp. 147–188). Annual Reviews Inc.
Roth, D. (1995). Learning to reason: The non-monotonic case. Proceedings of the International Joint Conference of Artificial Intelligence (pp. 1178–1184). Montreal, Canada: Morgan Kaufmann.
Schuurmans, D., & Greiner, R. (1994). Learning default concepts. Proceedings of the Tenth Canadian Conference on Artificial Intelligence (CSCSI-94) (pp. 519–523).
Selman, B., & Kautz, H. (1996). Knowledge compilation and theory approximation. Journal of the ACM, 43(2), 193–224.
Valiant, L.G. (1984). A theory of the learnable. Communications of the ACM, 27(11), 1134–1142.
Valiant, L.G. (1995). Rationality. Proceedings of the Conference on Computational Learning Theory (pp. 3–14). Santa Cruz, CA: ACM Press.
Author information
Authors and Affiliations
Rights and permissions
About this article
Cite this article
Khardon, R., Roth, D. Learning to Reason with a Restricted View. Machine Learning 35, 95–116 (1999). https://doi.org/10.1023/A:1007581123604
Issue Date:
DOI: https://doi.org/10.1023/A:1007581123604