论文信息 - On the ability of the optimal perceptron to generalise - 字舞流文

On the ability of the optimal perceptron to generalise

A linearly separable Boolean function is derived from a set of examples by a perceptron with optimal stability. The probability to reconstruct a pattern which is not learnt is calculated analytically using the replica method.

M. Opper | W. Kinzel | J. Kleinz | R. Nehl

[1] W. Krauth,et al. Learning algorithms with optimal stability in neural networks , 1987 .

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

[3] E. Gardner,et al. Optimal storage properties of neural network models , 1988 .

[4] Opper. Learning times of neural networks: Exact solution for a PERCEPTRON algorithm. , 1988, Physical review. A, General physics.

[5] E. Gardner. The space of interactions in neural network models , 1988 .

[6] F. Vallet. The Hebb Rule for Learning Linearly Separable Boolean Functions: Learning and Generalization , 1989 .

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

[8] Michael Biehl,et al. The AdaTron: An Adaptive Perceptron Algorithm , 1989 .

[9] Wolfgang Kinzel,et al. Dynamics of learning , 1991 .