Learning to reason

Roni Khardon, Dan Roth

Research output: Contribution to conferencePaper

Abstract

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 show how previous results from learning theory and reasoning fit into this framework 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 a Learning to Reason algorithm for a class 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 known to be learnable in the traditional sense.

Original languageEnglish (US)
Pages682-687
Number of pages6
StatePublished - Dec 1 1994
EventProceedings of the 12th National Conference on Artificial Intelligence. Part 1 (of 2) - Seattle, WA, USA
Duration: Jul 31 1994Aug 4 1994

Other

OtherProceedings of the 12th National Conference on Artificial Intelligence. Part 1 (of 2)
CitySeattle, WA, USA
Period7/31/948/4/94

ASJC Scopus subject areas

  • Software
  • Artificial Intelligence

Cite this

Khardon, R., & Roth, D. (1994). Learning to reason. 682-687. Paper presented at Proceedings of the 12th National Conference on Artificial Intelligence. Part 1 (of 2), Seattle, WA, USA, .

Learning to reason. / Khardon, Roni; Roth, Dan.

1994. 682-687 Paper presented at Proceedings of the 12th National Conference on Artificial Intelligence. Part 1 (of 2), Seattle, WA, USA, .

Research output: Contribution to conferencePaper

Khardon, R & Roth, D 1994, 'Learning to reason', Paper presented at Proceedings of the 12th National Conference on Artificial Intelligence. Part 1 (of 2), Seattle, WA, USA, 7/31/94 - 8/4/94 pp. 682-687.
Khardon R, Roth D. Learning to reason. 1994. Paper presented at Proceedings of the 12th National Conference on Artificial Intelligence. Part 1 (of 2), Seattle, WA, USA, .
Khardon, Roni ; Roth, Dan. / Learning to reason. Paper presented at Proceedings of the 12th National Conference on Artificial Intelligence. Part 1 (of 2), Seattle, WA, USA, .6 p.
@conference{a15c56d17c384f9bb53b2801cec61d39,
title = "Learning to reason",
abstract = "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 show how previous results from learning theory and reasoning fit into this framework 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 a Learning to Reason algorithm for a class 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 known to be learnable in the traditional sense.",
author = "Roni Khardon and Dan Roth",
year = "1994",
month = "12",
day = "1",
language = "English (US)",
pages = "682--687",
note = "Proceedings of the 12th National Conference on Artificial Intelligence. Part 1 (of 2) ; Conference date: 31-07-1994 Through 04-08-1994",

}

TY - CONF

T1 - Learning to reason

AU - Khardon, Roni

AU - Roth, Dan

PY - 1994/12/1

Y1 - 1994/12/1

N2 - 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 show how previous results from learning theory and reasoning fit into this framework 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 a Learning to Reason algorithm for a class 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 known to be learnable in the traditional sense.

AB - 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 show how previous results from learning theory and reasoning fit into this framework 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 a Learning to Reason algorithm for a class 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 known to be learnable in the traditional sense.

UR - http://www.scopus.com/inward/record.url?scp=0028583046&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0028583046&partnerID=8YFLogxK

M3 - Paper

AN - SCOPUS:0028583046

SP - 682

EP - 687

ER -