Finite-state neural networks. A step toward the simulation of very large systems
- Hoechstleistungsrechenzentrum an der KFA Juelich (West Germany)
Neural networks composed of neurons with Q{sub N} states and synapses with Q{sub J} states are studied analytically and numerically. Analytically it is shown that these finite-state networks are much more efficient at information storage than networks with continuous synapses. In order to take the utmost advantage of networks with finite-state elements, a multineuron and multisynapse coding scheme is introduced which allows the simulation of networks having 1.0 {times} 10{sup 9} couplings at a speed of 7.1 {times} 10{sup 9} coupling evaluations per second on a single processor of the Cray-YMP. A local learning algorithm is also introduced which allows for the efficient training of large networks with finite-state elements.
- OSTI ID:
- 5292056
- Journal Information:
- Journal of Statistical Physics; (United States), Vol. 62:3-4; ISSN 0022-4715
- Country of Publication:
- United States
- Language:
- English
Similar Records
Neural network simulations on massively parallel computers: Applications in chemical physics
Neural network simulations on massively parallel computers: Applications in chemical physics