Dual Field Approach to Correlation Functions in the Heisenberg Xxz Spin Chain
(1995)
Modern Analytic Techniques to Solve the Dynamics of Recurrent Neural Networks
Advances in Neural Information Processing Systems 8 (1995) 253-259
Abstract:
We describe the use of modern analytical techniques in solving the dynamics of symmetric and nonsymmetric recurrent neural networks near saturation. These explicitly take into account the correlations between the post-synaptic potentials, and thereby allow for a reliable prediction of transients.A memory model with novel behaviour in sequential learning
Network Computation in Neural Systems Taylor & Francis 6:3 (1995) 415-427