Title :
Encoding temporal structure in probabilistic RAM nets
Author :
Gorse, D. ; Taylor, J.G.
Author_Institution :
Univ. Coll. London
Abstract :
The authors show how both gradient descent and reinforcement training can be used to teach a recurrent probabilistic RAM (pRAM) net to classify binary strings of arbitrary length, and how a form of reinforcement training can be used with `leaky integrator´ pRAM nodes to enable them to store complex temporal sequences
Keywords :
learning systems; neural nets; probabilistic logic; binary string classification; complex temporal sequences; gradient descent; grammatical structure learning; leaky integrator; pRAM; probabilistic RAM nets; recurrent probabilistic RAM; regular grammar; reinforcement training;
Conference_Titel :
Artificial Neural Networks, 1991., Second International Conference on
Conference_Location :
Bournemouth
Print_ISBN :
0-85296-531-1
