Storage capacity and generalization error for the reversed-wedge Ising perceptron
- 1 June 1995
- journal article
- research article
- Published by American Physical Society (APS) in Physical Review E
- Vol. 51 (6) , 6309-6312
- https://doi.org/10.1103/physreve.51.6309
Abstract
Using the replica formalism, we evaluate the storage capacity and the generalization error of a perceptron with a reversed-wedge transfer function and binary synaptic weights. Remarkably, both the storage capacity and the generalization threshold saturate the information theoretic (respectively upper and lower) bound α=1 for a specific choice of the width of the reverse wedge, suggesting that this perceptron may be an interesting building block for neural networks.Keywords
This publication has 20 references indexed in Scilit:
- Clipped-Hebbian Training of the PerceptronEurophysics Letters, 1993
- The statistical mechanics of learning a ruleReviews of Modern Physics, 1993
- Statistical mechanics of learning from examplesPhysical Review A, 1992
- Finite-size effects and bounds for perceptron modelsJournal of Physics A: General Physics, 1991
- Learning from examples in large neural networksPhysical Review Letters, 1990
- First-order transition to perfect generalization in a neural network with binary synapsesPhysical Review A, 1990
- Three unfinished works on the optimal storage capacity of networksJournal of Physics A: General Physics, 1989
- Critical storage capacity of the J = ± 1 neural networkJournal of Physics A: General Physics, 1989
- Storage capacity of memory networks with binary couplingsJournal de Physique, 1989
- Optimal storage properties of neural network modelsJournal of Physics A: General Physics, 1988