Efficient Agnostic Learning of Neural Networks with Bounded Fan-in

Efficient Agnostic Learning of Neural Networks with Bounded Fan-in (1996)

Cached

Download Links

[www.comp.nus.edu.sg]
[wwwsyseng.anu.edu.au]

Other Repositories/Bibliography

DBLP

by Wee Sun Lee , Peter L. Bartlett , Robert C. Williamson

Citations:

57 - 18 self

BibTeX

@MISC{Lee96efficientagnostic,
    author = {Wee Sun Lee and Peter L. Bartlett and Robert C. Williamson},
    title = {Efficient Agnostic Learning of Neural Networks with Bounded Fan-in},
    year = {1996}
}

Years of Citing Articles

Bookmark

OpenURL

Abstract

We show that the class of two layer neural networks with bounded fan-in is efficiently learnable in a realistic extension to the Probably Approximately Correct (PAC) learning model. In this model, a joint probability distribution is assumed to exist on the observations and the learner is required to approximate the neural network which minimizes the expected quadratic error. As special cases, the model allows learning real-valued functions with bounded noise, learning probabilistic concepts and learning the best approximation to a target function that cannot be well approximated by the neural network. The networks we consider have real-valued inputs and outputs, an unlimited number of threshold hidden units with bounded fan-in, and a bound on the sum of the absolute values of the output weights. The number of computation This work was supported by the Australian Research Council and the Australian Telecommunications and Electronics Research Board. The material in this paper was pres...

Citations

2304	Learning Internal Representations by Error Propagation - Rumelhart, Hinton, et al. - 1986
2172	The Design and Analysis of Computer Algorithms - Aho, Hopcroft, et al. - 1974
1515	A Theory of the Learnable - Valiant - 1984
933	A training algorithm for optimal margin classifiers - Boser, Guyon, et al. - 1992
816	On the uniform convergence of relative frequencies of events to their probabilities. Theory of Prob. and its - Vapnik, Chervonenkis - 1971
457	Convergence of Stochastic Processes - Pollard - 1984
328	Decision theoretic generalization of the PAC model for neural net and other learning applications - Haussler - 1992
313	Universal approximation bounds for superpositions of a sigmoidal function - Barron - 1993
205	On the density of families of sets - Sauer - 1972
186	Training a 3-node neural networks is np-complete - Blum, Rivest - 1992
182	Efficient distributionfree learning of probabilistic concepts - Kearns, Schapire - 1994
169	Toward efficient agnostic learning - KEARNS, SCHAPIRE, et al. - 1994
123	Universal approximation of an unknown mapping and its derivatives using multilayer feedforward networks - Hornik, Stichcombe, et al. - 1990
112	A simple lemma on greedy approximation in Hilbert space and convergence rates for projection pursuit regression and neural network training. The Annals of Statistics - Jones - 1992
107	Approximation and estimation bounds for artificial neural networks - BARRON - 1994
87	Neural Network design and the complexity of learning - Judd - 1990
66	Complexity regularization with applications to artificial neural networks - BARRON - 1991
36	The importance of convexity in learning with squared loss - Lee, Bartlett, et al. - 1998
33	Computational Learning Theory. Cambridge Tracts - Anthony, Biggs - 1992
25	Neural net approximation - Barron - 1992
23	Bounding sample size with the Vapnik–Chervonenkis dimension - Shawe-Taylor, Anthony, et al. - 1993
20	Agnostic PAC-learning of functions on analog neural nets - Maass - 1994
17	Strong universal consistency of neural network classifiers - Faragó, Lugosi - 1993
13	Convergence rates for single hidden layer feedforward networks - McCaffrey, Gallant - 1994
12	Efficient learning of continuous neural networks - Koiran - 1994
12	On efficient agnostic learning of linear combinations of basis functions - Lee, Bartlett, et al. - 1995
10	On the tchebychef inequality of bernstein,” The - Craig - 1933
8	Uniform ratio limit theorems for empirical processes - Pollard - 1995
5	Simple translation-invariant concepts are hard to learn - Jerrum - 1991