On the ability of the optimal perceptron to generalise
- 7 June 1990
- journal article
- Published by IOP Publishing in Journal of Physics A: General Physics
- Vol. 23 (11) , L581-L586
- https://doi.org/10.1088/0305-4470/23/11/012
Abstract
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.Keywords
This publication has 8 references indexed in Scilit:
- The AdaTron: An Adaptive Perceptron AlgorithmEurophysics Letters, 1989
- Linear and Nonlinear Extension of the Pseudo-Inverse Solution for Learning Boolean FunctionsEurophysics Letters, 1989
- The Hebb Rule for Learning Linearly Separable Boolean Functions: Learning and GeneralizationEurophysics Letters, 1989
- Learning times of neural networks: Exact solution for a PERCEPTRON algorithmPhysical Review A, 1988
- Optimal storage properties of neural network modelsJournal of Physics A: General Physics, 1988
- The space of interactions in neural network modelsJournal of Physics A: General Physics, 1988
- Learning algorithms with optimal stability in neural networksJournal of Physics A: General Physics, 1987
- Learning of correlated patterns in spin-glass networks by local learning rulesPhysical Review Letters, 1987