On the ability of the optimal perceptron to generalise
作者： M Opper , W Kinzel , J Kleinz , R Nehl
DOI: 10.1088/0305-4470/23/11/012
关键词:
摘要: A linearly separable Boolean function is derived from a set of examples by perceptron with optimal stability. The probability to reconstruct pattern which not learnt calculated analytically using the replica method.
harvard.edu
sci-hub.se 参考文章(9)
Wolfgang Kinzel, Manfred Opper, Dynamics of learning Models of neural networks. pp. 149- 171 ,(1991) , 10.1007/978-3-642-79814-6_4
F Vallet, The Hebb Rule for Learning Linearly Separable Boolean Functions: Learning and Generalization EPL. ,vol. 8, pp. 747- 751 ,(1989) , 10.1209/0295-5075/8/8/007
M. Opper, Learning times of neural networks: Exact solution for a PERCEPTRON algorithm. Physical Review A. ,vol. 38, pp. 3824- 3826 ,(1988) , 10.1103/PHYSREVA.38.3824
F Vallet, J.-G Cailton, Ph Refregier, Linear and nonlinear extension of the pseudo-inverse solution for learning Boolean functions EPL. ,vol. 9, pp. 315- 320 ,(1989) , 10.1209/0295-5075/9/4/003
Sigurd Diederich, Manfred Opper, Learning of correlated patterns in spin-glass networks by local learning rules. Physical Review Letters. ,vol. 58, pp. 949- 952 ,(1987) , 10.1103/PHYSREVLETT.58.949
E Gardner, B Derrida, Optimal storage properties of neural network models Journal of Physics A. ,vol. 21, pp. 271- 284 ,(1988) , 10.1088/0305-4470/21/1/031
E Gardner, The space of interactions in neural network models Journal of Physics A. ,vol. 21, pp. 257- 270 ,(1988) , 10.1088/0305-4470/21/1/030
W Krauth, M Mezard, Learning algorithms with optimal stability in neural networks Journal of Physics A. ,vol. 20, ,(1987) , 10.1088/0305-4470/20/11/013
J. K Anlauf, M Biehl, The AdaTron: An Adaptive Perceptron Algorithm EPL. ,vol. 10, pp. 687- 692 ,(1989) , 10.1209/0295-5075/10/7/014