On learning sets and functions

This paper presents some results on the probabilistic analysis of learning, illustrating the applicability of these results to settings such as connectionist networks. In particular, it concerns the learning of sets and functions from examples and background information. After a formal statement of the problem, some theorems are provided identifying the conditions necessary and sufficient for efficient learning, with respect to measures of information complexity and computational complexity. Intuitive interpretations of the definitions and theorems are provided.

[1]  Vladimir Vapnik,et al.  Chervonenkis: On the uniform convergence of relative frequencies of events to their probabilities , 1971 .

[2]  John T. Gill,et al.  Computational complexity of probabilistic Turing machines , 1974, STOC '74.

[3]  Carl H. Smith,et al.  Inductive Inference: Theory and Methods , 1983, CSUR.

[4]  D. Pollard.  Convergence of stochastic processes , 1984 .

[5]  Leslie G. Valiant,et al.  A theory of the learnable , 1984, CACM.

[6]  David Haussler,et al.  Classifying learnable geometric concepts with the Vapnik-Chervonenkis dimension , 1986, STOC '86.

[7]  Tom Michael Mitchell,et al.  Explanation-based generalization: A unifying view , 1986 .

[8]  이종원,et al.  Explanation - Based Generalization 의 문제점 및 이의 해결방안 , 1986 .

[9]  Piotr Berman,et al.  Learning one-counter languages in polynomial time , 1987, 28th Annual Symposium on Foundations of Computer Science (sfcs 1987).

[10]  Ronald L. Rivest,et al.  Diversity-based inference of finite automata , 1994, 28th Annual Symposium on Foundations of Computer Science (sfcs 1987).

[11]  Balas K. Natarajan,et al.  On learning Boolean functions , 1987, STOC.

[12]  Dana Angluin,et al.  Learning Regular Sets from Queries and Counterexamples , 1987, Inf. Comput..

[13]  Leslie G. Valiant,et al.  On the learnability of Boolean formulae , 1987, STOC.

[14]  N. Littlestone.  Learning Quickly When Irrelevant Attributes Abound: A New Linear-Threshold Algorithm , 1987, 28th Annual Symposium on Foundations of Computer Science (sfcs 1987).

[15]  M. Kearns,et al.  Recent Results on Boolean Concept Learning , 1987 .

[16]  Leonard Pitt,et al.  Reductions among prediction problems: on the difficulty of predicting automata , 1988, [1988] Proceedings. Structure in Complexity Theory Third Annual Conference.

[17]  Prasad Tadepalli,et al.  Two New Frameworks for Learning , 1988, ML.

[18]  David Haussler,et al.  Predicting {0,1}-functions on randomly drawn points , 1988, COLT '88.

[19]  Balas K. Natarajan,et al.  On learning from exercises , 1989, COLT '89.

[20]  B. K. Natarajan,et al.  Some results on learning , 1989 .

[21]  Ronald L. Rivest,et al.  Training a 3-node neural network is NP-complete , 1988, COLT '88.

[22]  Ronald L. Rivest,et al.  Learning decision lists , 2004, Machine Learning.

[23]  D. Angluin,et al.  Learning From Noisy Examples , 1988, Machine Learning.