Distribution of internal fields and dynamics of neural networks
暂无分享,去创建一个
A new approach to treat the temporal development of fully connected neural networks is introduced. It is based on a non-Gaussian ansatz for the distribution of internal fields, incorporating memory effects. For the network with projector couplings recursion relations for the parameters of the field distribution are derived, which yield remanence effects as well as basins of attractions in good agreement with numerical simulations.
[1] J. Chayes,et al. The phase boundary in dilute and random Ising and Potts ferromagnets , 1987 .
[2] Y. Shapir,et al. Improved kinetic renormalisation group approach to diffusion-limited aggregation , 1989 .