One-Shot Learners Using Negative Counterexamples and Nearest Positive Examples

Authors:
Sanjay Jain;Efim Kinber
Affiliations:
School of Computing, National University of Singapore, 117590, Singapore;Department of Computer Science, Sacred Heart University, Fairfield, CT 06432-1000, U.S.A.
Venue:
ALT '07 Proceedings of the 18th international conference on Algorithmic Learning Theory
Year:
2007

Citing 10
Cited 2

Theory of recursive functions and effective computability

Theory of recursive functions and effective computability
Learning via queries

Journal of the ACM (JACM)
Queries and Concept Learning

Machine Learning
Queries and Concept Learning

Machine Learning
A Guided Tour Across the Boundaries of Learning Recursive Languages

Algorithmic Learning for Knowledge-Based Systems, GOSLER Final Report
Formal language identification: query learning vs. gold-style learning

Information Processing Letters
Learning languages from positive data and negative counterexamples

Journal of Computer and System Sciences
Relations between Gold-style learning and query learning

Information and Computation
Gold-style and query learning under various constraints on the target class

ALT'05 Proceedings of the 16th international conference on Algorithmic Learning Theory
Learning DFA from correction and equivalence queries

ICGI'06 Proceedings of the 8th international conference on Grammatical Inference: algorithms and applications

A Note on the Relationship between Different Types of Correction Queries

ICGI '08 Proceedings of the 9th international colloquium on Grammatical Inference: Algorithms and Applications
Necessary and sufficient conditions for learning with correction queries

Theoretical Computer Science

Quantified Score

Hi-index	0.00

Visualization

Abstract

As some cognitive research suggests, in the process of learning languages, in addition to overtexplicit negative evidence, a child often receives covertexplicit evidence in form of corrected or rephrased sentences. In this paper, we suggest one approach to formalization of overt and covert evidence within the framework of one-shotlearners via subset and membership queries to a teacher (oracle). We compare and explore general capabilities of our models, as well as complexity advantages of learnability models of one type over models of other types, where complexity is measured in terms of number of queries. In particular, we establish that "correcting" positive examples give sometimes more power to a learner than just negative (counter)examples and access to full positive data.