A pulse-based reinforcement algorithm for learning continuous functions.
319 - 344.
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.
|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
UCL > School of BEAMS > Faculty of Engineering Science
Archive Staff Only