Stochastic computing and reinforcement neural networks
Richard A. Leaver, P. Mars · International Conference on Artificial Neural Networks · 1989
This paper considers reinforcement learning neural networks using associative reward/penalty elements. Fundamental theory and applications of relevant stochastic learning automata are reviewed followed by a discussion of associative reward/penalty structures and recent work on reinforcement neural networks. The paper concludes with a consideration of the use of stochastic computing techniques for the hardware synthesis of neural networks. >