Computational limitations on learning from examples-Reference-Cited by-同舟云学术

Computational limitations on learning from examples

Published:1988-10 Issue:4 Volume:35 Page:965-984
ISSN:0004-5411
Container-title:Journal of the ACM
language:en
Short-container-title:J. ACM

Author:

Pitt Leonard¹,Valiant Leslie G.²

Affiliation:

1. Univ. of Illinois, Urbana-Champaign, Urbana

2. Harvard Univ., Cambridge, MA

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.

Publisher

Association for Computing Machinery (ACM)

Subject

Artificial Intelligence,Hardware and Architecture,Information Systems,Control and Systems Engineering,Software

Link

https://dl.acm.org/doi/pdf/10.1145/48014.63140

Reference33 articles.

1. On the complexity of minimum inference of regular sets;ANGLUIN D;Inf. Control,1978

2. Finding patterns common to a set of strings;ANGLUIN D;J. Comput. Syst. Sci.,1980

3. inference of formal languages from positive data;ANGLUIN D.;Inf. Control,1980

4. Inference of Reversible Languages

5. ANGLUIN D. Remarks on the difficulty of finding a minimal disjunctive normal form for Boolean functions. Unpublished manuscript. ANGLUIN D. Remarks on the difficulty of finding a minimal disjunctive normal form for Boolean functions. Unpublished manuscript.

Cited by 312 articles. 订阅此论文施引文献订阅此论文施引文献，注册后可以免费订阅5篇论文的施引文献，订阅后可以查看论文全部施引文献

1. The evolving hierarchy of naturalized philosophy: A metaphilosophical sketch;Metaphilosophy;2024-06-26

2. On the computational complexity of ethics: moral tractability for minds and machines;Artificial Intelligence Review;2024-03-31

3. On the non-efficient PAC learnability of conjunctive queries;Information Processing Letters;2024-01

4. Einführung;Maschinelles Lernen;2024

5. A circuit complexity formulation of algorithmic information theory;Physica D: Nonlinear Phenomena;2023-12