论文信息 - Generalization ability of perceptrons with continuous outputs.

Generalization ability of perceptrons with continuous outputs.

In this paper we examine the influence of different input-output relations on the generalization ability of a single-layer perceptron. The input-output relations can be linear, binary, or sigmoid. With this choice we take into account most of the cases which are of present interest. The generalization problem will be realizable or unrealizable if the input-output relations for teacher and student are identical or not. We show that sometimes it can have a positive effect on the generalization ability, if one learns with errors.

Opper | Boes | Kinzel

[1] James L. McClelland,et al. Parallel distributed processing: explorations in the microstructure of cognition, vol. 1: foundations , 1986 .

[2] Opper,et al. Learning of correlated patterns in spin-glass networks by local learning rules. , 1987, Physical review letters.

[3] Kanter,et al. Associative recall of memory without errors. , 1987, Physical review. A, General physics.

[4] F. Vallet,et al. Linear and Nonlinear Extension of the Pseudo-Inverse Solution for Learning Boolean Functions , 1989 .

[5] M. Opper,et al. On the ability of the optimal perceptron to generalise , 1990 .

[6] Wolfgang Kinzel,et al. Improving a Network Generalization Ability by Selecting Examples , 1990 .

[7] Petri Koistinen,et al. Using additive noise in back-propagation training , 1992, IEEE Trans. Neural Networks.

[8] Sompolinsky,et al. Statistical mechanics of learning from examples. , 1992, Physical review. A, Atomic, molecular, and optical physics.

[9] A. Krogh. Learning with noise in a linear perceptron , 1992 .

[10] T. Watkin,et al. Selecting examples for perceptrons , 1992 .

[11] J. Hertz,et al. Generalization in a linear perceptron in the presence of noise , 1992 .