Dynamics of fully connected attractor neural networks near saturation.
Phys Rev Lett 71:23 (1993) 3886-3889
Coupled dynamics of fast spins and slow interactions: An alternative perspective on replicas.
Phys Rev B Condens Matter 48:21 (1993) 16116-16118
EQUILIBRIUM DISTRIBUTIONS OF STOCHASTIC NETWORKS WITHOUT DETAILED BALANCE
PHYSICA A 200:1-4 (1993) 602-607
Fast learning of biased patterns in neural networks.
Int J Neural Syst 4:3 (1993) 223-230
Abstract:
Usual neural network gradient descent training algorithms require training times of the same order as the number of neurons N if the patterns are biased. In this paper, modified algorithms are presented which require training times equal to those in unbiased cases which are of order 1. Exact convergence proofs are given. Gain parameters which produce minimal learning times in large networks are computed by replica methods. It is demonstrated how these modified algorithms are applied in order to produce four types of solutions to the learning problem: 1. A solution with all internal fields equal to the desired output, 2. The Adaline (or pseudo-inverse) solution, 3. The perceptron of optimal stability without threshold and 4. The perceptron of optimal stability with threshold.Neural networks optimally trained with noisy data.
Phys Rev E Stat Phys Plasmas Fluids Relat Interdiscip Topics 47:6 (1993) 4465-4482