Article ID: | iaor20013566 |
Country: | Japan |
Volume: | 43 |
Issue: | 4 |
Start Page Number: | 469 |
End Page Number: | 485 |
Publication Date: | Dec 2000 |
Journal: | Journal of the Operations Research Society of Japan |
Authors: | Okano Hiroyuki, Koda Masato |
Keywords: | cybernetics, learning |
A new stochastic learning algorithm using Gaussian white noise sequence, referred to as Subconscious Noise Reaction (SNR), is proposed for a class of discrete-time neural networks with time-dependent connection weights. Unlike the back-propagation-through-time algorithm, SNR does not require the synchronous transmission of information backward along connection weights, while it uses only ubiquitous noise and local signals, which are correlated against a single performance functional, to achieve simple sequential (chronologically ordered) updating of connection weights. The algorithm is derived and analyzed on the basis of a functional derivative formulation of the gradient descent method in conjunction with stochastic sensitivity analysis techniques using the variational approach.