Input-Dependence in Function-Learning

Authors:
Sanjay Jain;Eric Martin;Frank Stephan
Affiliations:
Department of Computer Science, National University of Singapore, Singapore 117543, Republic of Singapore;Department of Computer Science and Engineering, The University of New South Wales, Sydney 2052, NSW, Commonwealth of Australia;Department of Mathematics, National University of Singapore, Singapore 117543, Republic of Singapore
Venue:
CiE '07 Proceedings of the 3rd conference on Computability in Europe: Computation and Logic in the Real World
Year:
2007

Citing 6
Cited 0

Systems that learn: an introduction to learning theory for cognitive and computer scientists

Systems that learn: an introduction to learning theory for cognitive and computer scientists
Recursively enumerable sets and degrees

Recursively enumerable sets and degrees
Probability and plurality for aggregations of learning machines

Information and Computation
On the non-existence of maximal inference degrees for language identification

Information Processing Letters
On the structure of degrees of inferability

Journal of Computer and System Sciences
Computational limits on team identification of languages

Information and Computation

Quantified Score

Hi-index	0.00

Visualization

Abstract

In the standard literature on inductive inference, a learner sees as input the course of values of the function to be learned. In the present work, it is investigated how reasonable this choice is and how sensitive the model is with respect to variations like the overgraph or undergraph of the function. Several implications and separations are shown and for the basic notions, a complete picture is obtained. Furthermore, relations to oracles, additional information and teams are explored.