Title :
Stochastic and deterministic neural networks with a continuous state space and a connectivity greater than two
Author :
Lacaille, Jérôme
Author_Institution :
Ecole Nat. Superieure de Cachen, France
fDate :
27 Jun-2 Jul 1994
Abstract :
This article is divided into two parts, which both give a detailed observation of a particular type of recurrent network, presenting cells which activities continuously evolve in an interval of R. The first part of this article shows a stochastic type of network derived from Boltzmann machines, whereas the second part is devoted to determinist process. In both cases, we will formalize the dynamic system, and give an algorithm of relaxation and learning
Keywords :
Boltzmann machines; recurrent neural nets; Boltzmann machines; continuous state space; deterministic neural net; recurrent neural net; stochastic neural net; Density measurement; Equations; Machine learning; Neural networks; Recurrent neural networks; State-space methods; Stochastic processes;
Conference_Titel :
Neural Networks, 1994. IEEE World Congress on Computational Intelligence., 1994 IEEE International Conference on
Conference_Location :
Orlando, FL
Print_ISBN :
0-7803-1901-X
DOI :
10.1109/ICNN.1994.374304
