Title :
Stochastic arithmetic implementations of neural networks with in situ learning
Author :
Dickson, Jeffrey A. ; McLeod, Robert D. ; Card, Howard C.
Author_Institution :
Dept. of Electr. & Comput. Eng., Manitoba Univ., Winnipeg, Man., Canada
Abstract :
The implementation of artificial neural networks using stochastic arithmetic capable of in situ learning is described. Stochastic arithmetic uses values encoded as a pulse density, and allows addition, multiplication, and the nonlinearity to be implemented in a very small amount of digital hardware. A VLSI implementation of such a network is capable of processing 100000 training vectors per second. The performance of this architecture is demonstrated by two examples
Keywords :
VLSI; digital arithmetic; learning systems; neural nets; parallel architectures; VLSI implementation; neural networks; parallel architecture; pulse density; situ learning; stochastic arithmetic; Artificial neural networks; Computer architecture; Digital arithmetic; Hardware; Intelligent networks; Linearity; Neural networks; Neurons; Stochastic processes; Very large scale integration;
Conference_Titel :
Neural Networks, 1993., IEEE International Conference on
Conference_Location :
San Francisco, CA
Print_ISBN :
0-7803-0999-5
DOI :
10.1109/ICNN.1993.298642
