article

Free access

Learning to reason

Authors:

Dan RothAuthors Info & Claims

Journal of the ACM (JACM), Volume 44, Issue 5

Pages 697 - 725

https://doi.org/10.1145/265910.265918

Published: 01 September 1997 Publication History

Abstract

We introduce a new framework for the study of reasoning. The Learning (in order) to Reason approach developed here views learning as an integral part of the inference process, and suggests that learning and reasoning should be studied together.

The Learning to Reason framework combines the interfaces to the world used by known learning models with the reasoning task and a performance criterion suitable for it. In this framework, the intelligent agent is given access to its favorite learning interface, and is also given a grace period in with it can interact with this interface and construct a representation KB of the world W. The reasoning performance is measured only after this period, when the agent is presented with queries α from some query language, relevant to the world, and has to answer whether W implies α.

The approach is meant to overcome the main computational difficulties in the traditional treatment of reasoning which stem from its separation from the “world”. Since the agent interacts with the world when construction its knowledge representation it can choose a representation that is useful for the task at hand. Moreover, we can now make explicit the dependence of the reasoning performance on the environment the agent interacts with.

We show how previous results from learning theory and reasoning fit into this framwork and illustrate the usefulness of the Learning to Reason approach by exhibiting new results that are not possible in the traditional setting. First, we give Learning to Reason algorithms for classes of propositional languages for which there are no efficient reasoning algorithms, when represented as a traditional (formula-based) knowledge base. Second, we exhibit a Learning to Reason algorithm for a class of propositional languages that is not know to be learnable in the traditional sense.

References

[1]

AMSTERDAM, J. 1988. Extending the Valiant learning model. In Proceeding of the 5th International Workshop on Machine Learning. pp. 364-375.

[2]

ANGLUIN, D. 1988. Queries and concept learning. Mach. Learn. 2, 4 (Apr.), 319-342.

[3]

ANGLUIN, D. 1992. Computational learning theory: Survey and selected bibliography. In Proceedings of the 24th Annual ACM Symposium on Theory of Computing (Victoria, B.C., Canada, May 4-6). ACM, New York, pp. 351-369.

[4]

ANGLUIN, D., AND LAIRD, P. 1988. Learning from noisy examples. Mach. Learn. 2, 4, 343-370.

[5]

ANGLUIN, D., AND SLONIM, D.K. 1994. Randomly fallible teachers: Learning monotone DNF with an incomplete membership oracle. Mach. Learn. 19, 7-126.

[6]

BACCHUS, F., GROVE, A., HALPERN, J. Y., AND KOLLER, D. 1993. Statistical foundations for default reasoning. In Proceedings of the International Joint Conference of Artificial Intelligence. 563-569.

[7]

BACCHUS, F., GROVE, A., HALPERN, J. Y., AND KOLLER, D. 1996. From statistical knowledge bases to degrees of beliefs. Artif. Int. 87, 1-2, 75-143.

[8]

BROOKS, R.A. 1991. Intelligence without representation. Artif. Int. 47, 139-159.

[9]

BSHOUTY, N.H. 1995. Exact learning via the monotone theory. Inf. Comput. 123, 1, 146-153.

[10]

CADOLI, M. 1995. Tractable Reasoning in Artificial Intelligence. In Lecture Notes in Artificial Intelligence, vol. 941. Springer-Verlag, New York.

[11]

DECHTER, R., AND PEARL, J. 1992. Structure identification in relational data. Artif. Int. 58, 237-270.

[12]

DOYLE, J., AND PATIL, R. 1991. Two theses of knowledge representation: Language restrictions, taxonomic classification, and the utility of representation services./trtif. Int. 48, 261-297.

[13]

FAGIN, R., HALPERN, J. Y., MOSES, Y., AND VARDI, M.Y. 1995. Reasoning about Knowledge. MIT Press, Cambridge, Mass.

[14]

FRAZIER, M., AND PITT. L. 1993. Learning from entailment: An application to propositional Horn sentences. In Proceedings of the International Conference on Machine Learning. Morgan-Kaufmann, San Mateo, Calif.

[15]

GREINER, R., GROVE, A., AND ROTH, D. 1996. Learning active classifiers. In Proceedings of the International Conference on Machine Learning.

[16]

HAUSSLER, D. 1987. Bias, version spaces and Valiant's learning framework. In Proceedings of the 4th International Workshop on Machine Learning. Univ. California, Irvine, Irvine, Calif.

[17]

HENRION, M. 1988. Propagating uncertainty in Bayesian networks by probabilistic logic sampling. In Uncertainty in Artificial Intelligence.

[18]

JACKSON, J. 1994. An efficient membership-query algorithm for learning DNF with respect to the uniform distribution. In Proceedings of the IEEE Symposium on Foundation of Computer Science. IEEE, New York, pp. 42-53.

[19]

KAUTZ, H., KEARNS, M., AND SELMAN, B. 1993. Reasoning with characteristic models. In Proceedings of the National Conference on Artificial Intelligence. pp. 34-39.

[20]

KAUTZ, H., KEARNS, M., AND SELMAN, B. 1995. Horn approximations of empirical data. Artif. Int. 74, 129-145.

[21]

KEARNS, M. 1992. Oblivious pac learning of concepts hierarchies. In Proceedings of the National Conference on Artificial Intelligence. pp. 215-222.

[22]

KEARNS, M., AND LI, M. 1988. Learning in the presence of malicious errors. In Proceedings of the 20th Annual ACM Symposium on Theory of Computing (Chicago, Ill., May 2-4). ACM, New York, pp. 267-280.

[23]

KHARDON, R. 1996. Learning to take actions. In Proceedings of the National Conference on Artificial Intelligence. pp. 787-792.

[24]

KHARDON, R., AND ROTH, D. 1995. Learning to reason with a restricted view. In Workshop on Computational Learning Theory. pp. 301-310.

[25]

KHARDON, R., AND ROTH, D. 1996. Reasoning with models. Artif. Int. 87, 1-2, 187-213.

[26]

KHARDON, R., AND ROTH, D. 1997. Default-reasoning with models. Artif. Int. J., to appear.

[27]

KmSH, D. 1991. Foundations of AI: The big issues. Artif. Int. 47, 3-30.

[28]

LEVESQUE, H.J. 1984. Foundations of a functional approach to knowledge representation. Artif. Int. 23, 155-212.

[29]

LEVESQUE, H. 1986. Making believers out of computers. Artif. Int. 30, 81-108.

[30]

LEVESQUE, H. 1992. Is reasoning too hard? In Proceeding of the 3rd NEC Research Symposium.

[31]

LEVESQUE, H., AND BRACHMAN, R. 1985. A fundamental tradeoff in knowledge representation and reasoning. In Readings in Knowledge Representation, R. Brachman and H. Levesque, eds. Morgan- Kaufman, San Mateo, Calif.

[32]

LITTLESTONE, N. 1988. Learning quickly when irrelevant attributes abound: A new linear-threshold algorithm. Mach. Learn. 2, 285-318.

[33]

MCCARTHY, J. 1985. Programs with common sense. In Readings in Knowledge Representation, 1985, R. Brachman and H. Levesque, eds. Morgan-Kaufmann, San Mateo, Calif.

[34]

MOSES, Y., AND TENNENHOLTZ, M. 1996. Off-line reasoning for on-line efficiency: Knowledge bases. Artif. Int. 83, 2, 229-239.

[35]

NILSSON, N.J. 1986.Probabilistic logic. Artif. Int. 28, 71-87.

[36]

NILSSON, N.J. 1991.Logic and artificial intelligence. Artif. Int. 47, 31-56.

[37]

PAPADIMITRIOU, C.H. 1991. On selecting a satisfying truth assignment. In Proceedings of the 32nd Annual IEEE Symposium on Foundations of Computer Science. IEEE, New York.

[38]

ROTH, D. 1995. Learning to reason: The non-monotonic case. In Proceedings of the International Joint Conference of Artificial Intelligence. pp. 1178-1184.

[39]

ROTH, D. 1996. On the hardness of approximate reasoning. Artif. Int. 82, 1-2 (Apr.), 273-302.

[40]

SELMAN, B. 1990. Tractable default reasoning. Ph.D. dissertation. Department of Computer Science, University of Toronto, Toronto, Ont., Canada.

[41]

SELMAN, B., AND KAUTZ, H. 1996. Knowledge compilation and theory approximation. J. ACM 43, 2 (Mar.), 193-224.

[42]

SHASTRI, L. 1993. A computational model of tractable reasoning--Taking inspiration from cognition. In Proceeding of the International Joint Conference of /trtificial Intelligence (Aug.). pp. 202-207.

[43]

VALIANT, L.G. 1984. A theory of the learnable. Commun./tCM 27, 11 (Nov.), 1134-1142.

[44]

VALIANT, L. G. 1985. Learning disjunctions of conjunctions. In Proceedings of the International Joint Conference of/trtificial Intelligence. Morgan-Kaufmann, San Mateo, Calif., pp. 560-566.

[45]

ALIANT, L.G. 1994. Circuits of the Mind (Nov.). Oxford University Press, Oxford, England.

[46]

VALIANT, L.G. 1994. Rationality. In Workshop on Computational Learning Theory (July). pp. 3-14.

[47]

VALIANT, k. G., AND VAZIRANI, V.V. 1986. NP is as easy as detecting unique solutions. Theoret. Comput. Sci. 47, 85-93.

Cited By

MOCANU IBELLE VJUBA B(2023)Learnability with PAC Semantics for Multi-agent BeliefsTheory and Practice of Logic Programming10.1017/S1471068423000182(1-18)Online publication date: 31-Jul-2023
https://doi.org/10.1017/S1471068423000182
Mocanu IBelle V(2023)Knowledge representation and acquisition in the era of large language models: Reflections on learning to reason via PAC-SemanticsNatural Language Processing Journal10.1016/j.nlp.2023.1000365(100036)Online publication date: Dec-2023
https://doi.org/10.1016/j.nlp.2023.100036
Tran TLe VLe HLe TZhu FChin Ooi BMiao CWang HSkrypnyk IHsu WChawla S(2021)From Deep Learning to Deep ReasoningProceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery & Data Mining10.1145/3447548.3470803(4076-4077)Online publication date: 14-Aug-2021
https://dl.acm.org/doi/10.1145/3447548.3470803
Show More Cited By

Index Terms

Learning to reason
1. Computing methodologies
  1. Artificial intelligence
    1. Knowledge representation and reasoning
  2. Machine learning
    1. Learning settings
    2. Machine learning approaches
      1. Rule learning
2. Theory of computation
  1. Logic

Recommendations

Learning in order to reason
Learning to reason
AAAI'94: Proceedings of the Twelfth AAAI National Conference on Artificial Intelligence

We introduce a new framework for the study of reasoning. The Learning (in order) to Reason approach developed here combines the interfaces to the world used by known learning models with the reasoning task and a performance criterion suitable for it.

We ...
A cumulative-model semantics for dynamic preferences on assumptions
IJCAI'97: Proceedings of the 15th international joint conference on Artifical intelligence - Volume 1

Explicit preferences on assumptions as used in prioritized circumscription [McCarthy, 1986; Lifschitz, 1985; Grosof, 1991] and preferred subtheories [Brewka, 1989] provide a clear and declarative method for defining preferred models. In this paper, we ...

Comments

Information & Contributors

Information

Published In

cover image Journal of the ACM

Journal of the ACM Volume 44, Issue 5

Sept. 1997

146 pages

ISSN:0004-5411

EISSN:1557-735X

DOI:10.1145/265910

Issue’s Table of Contents

Copyright © 1997 ACM.

Publisher

Association for Computing Machinery

New York, NY, United States

Publication History

Published: 01 September 1997

Published in JACM Volume 44, Issue 5

Permissions

Request permissions for this article.

Request Permissions

Check for updates

Author Tags

Qualifiers

Article

Contributors

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

37
Total Citations
View Citations
1,538
Total Downloads

Downloads (Last 12 months)158
Downloads (Last 6 weeks)30

Reflects downloads up to 09 Nov 2024

Other Metrics

View Author Metrics

Citations

Cited By

MOCANU IBELLE VJUBA B(2023)Learnability with PAC Semantics for Multi-agent BeliefsTheory and Practice of Logic Programming10.1017/S1471068423000182(1-18)Online publication date: 31-Jul-2023
https://doi.org/10.1017/S1471068423000182
Mocanu IBelle V(2023)Knowledge representation and acquisition in the era of large language models: Reflections on learning to reason via PAC-SemanticsNatural Language Processing Journal10.1016/j.nlp.2023.1000365(100036)Online publication date: Dec-2023
https://doi.org/10.1016/j.nlp.2023.100036
Tran TLe VLe HLe TZhu FChin Ooi BMiao CWang HSkrypnyk IHsu WChawla S(2021)From Deep Learning to Deep ReasoningProceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery & Data Mining10.1145/3447548.3470803(4076-4077)Online publication date: 14-Aug-2021
https://dl.acm.org/doi/10.1145/3447548.3470803
Juba B(2019)Polynomial-time probabilistic reasoning with partial observations via implicit learning in probability logicsProceedings of the Thirty-Third AAAI Conference on Artificial Intelligence and Thirty-First Innovative Applications of Artificial Intelligence Conference and Ninth AAAI Symposium on Educational Advances in Artificial Intelligence10.1609/aaai.v33i01.33017866(7866-7875)Online publication date: 27-Jan-2019
https://dl.acm.org/doi/10.1609/aaai.v33i01.33017866
Juba BLi ZMiller EMcIlraith SWeinberger K(2018)Learning abduction under partial observabilityProceedings of the Thirty-Second AAAI Conference on Artificial Intelligence and Thirtieth Innovative Applications of Artificial Intelligence Conference and Eighth AAAI Symposium on Educational Advances in Artificial Intelligence10.5555/3504035.3504265(1888-1896)Online publication date: 2-Feb-2018
https://dl.acm.org/doi/10.5555/3504035.3504265
Zhang MMathew TJuba BSingh SMarkovitch S(2017)An improved algorithm for learning to perform exception-tolerant abductionProceedings of the Thirty-First AAAI Conference on Artificial Intelligence10.5555/3298239.3298423(1257-1265)Online publication date: 4-Feb-2017
https://dl.acm.org/doi/10.5555/3298239.3298423
Hotaling LAngles M(2017)Blue futures: Engaging the next generationOCEANS 2017 - Aberdeen10.1109/OCEANSE.2017.8084675(1-7)Online publication date: Jun-2017
https://doi.org/10.1109/OCEANSE.2017.8084675
Juba BRoughgarden T(2015)Restricted Distribution Automatizability in PAC-SemanticsProceedings of the 2015 Conference on Innovations in Theoretical Computer Science10.1145/2688073.2688108(93-102)Online publication date: 11-Jan-2015
https://dl.acm.org/doi/10.1145/2688073.2688108
Gomes JSilver D(2015)Learning to reason in a Probably Approximately Correct manner2015 IEEE 28th Canadian Conference on Electrical and Computer Engineering (CCECE)10.1109/CCECE.2015.7129498(1475-1478)Online publication date: May-2015
https://doi.org/10.1109/CCECE.2015.7129498
(2015)The complexity of reasoning with FODD and GFODDArtificial Intelligence10.1016/j.artint.2015.08.005229:C(1-32)Online publication date: 1-Dec-2015
https://dl.acm.org/doi/10.1016/j.artint.2015.08.005
Show More Cited By

View Options

View options

PDF

View or Download as a PDF file.

eReader

View online with eReader.

Get Access

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