Computational limitations on learning from examples
- 1 October 1988
- journal article
- Published by Association for Computing Machinery (ACM) in Journal of the ACM
- Vol. 35 (4) , 965-984
- https://doi.org/10.1145/48014.63140
Abstract
The computational complexity of learning Boolean concepts from examples is investigated. It is shown for various classes of concept representations that these cannot be learned feasibly in a distribution-free sense unless R = NP. These classes include (a) disjunctions of two monomials, (b) Boolean threshold functions, and (c) Boolean formulas in which each variable occurs at most once. Relationships between learning of heuristics and finding approximate solutions to NP-hard optimization problems are given.Keywords
This publication has 17 references indexed in Scilit:
- Occam's RazorInformation Processing Letters, 1987
- Inductive Inference: Theory and MethodsACM Computing Surveys, 1983
- On the error correcting power of pluralism in BC-type inductive inferenceTheoretical Computer Science, 1983
- Comparison of identification criteria for machine inductive inferenceTheoretical Computer Science, 1983
- Inference of Reversible LanguagesJournal of the ACM, 1982
- Finding patterns common to a set of stringsJournal of Computer and System Sciences, 1980
- Inductive inference of formal languages from positive dataInformation and Control, 1980
- A Greedy Heuristic for the Set-Covering ProblemMathematics of Operations Research, 1979
- On the complexity of minimum inference of regular setsInformation and Control, 1978
- Toward a mathematical theory of inductive inferenceInformation and Control, 1975