Learning to reason with a restricted view

Roni Khardon, Dan Roth

Research output: Contribution to journalArticlepeer-review

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.

Original languageEnglish (US)
Pages (from-to)95-116
Number of pages22
JournalMachine Learning
Volume35
Issue number2
DOIs
StatePublished - 1999

ASJC Scopus subject areas

  • Software
  • Artificial Intelligence

Fingerprint

Dive into the research topics of 'Learning to reason with a restricted view'. Together they form a unique fingerprint.

Cite this