Gorse, D and RomanoCritchley, DA and Taylor, JG (1997) A pulse-based reinforcement algorithm for learning continuous functions. NEUROCOMPUTING , 14 (4) 319 - 344.
Full text not available from this repository.
Abstract
An algorithm is presented which allows continuous functions to be learned by a neural network using spike-based reinforcement learning, Both the mean and the variance of the weights are changed during training; the latter is accomplished by manipulating the lengths of the spike trains used to represent real-valued quantifies, The method is here applied to the probabilistic RAM (pRAM) model, but it may be adapted for use with any pulse-based stochastic model in which individual weights behave as random variables.
| Type: | Article |
|---|---|
| Title: | A pulse-based reinforcement algorithm for learning continuous functions |
| Keywords: | pRAM, continuous-output reinforcement, pulse-coding, stochastic computing, PROBABILISTIC RAM NETS, NEURAL NETWORKS, ELEMENTS |
| UCL classification: | UCL > School of BEAMS > Faculty of Engineering Science > Computer Science |
Archive Staff Only: edit this record