Mathematical foundations of neurocomputing
Journal Article
·
· Proceedings of the IEEE (Institute of Electrical and Electronics Engineers); (USA)
- Tokyo Univ. (Japan). Faculty of Engineering
Neurocomputing makes use of parallel dynamical interactions of modifiable neuron-like elements. It is important to show, by mathematical treatments, the capabilities and limitations of information processing by various architectures of neural networks. This paper, gives mathematical foundations to neurocomputing. It considers the capabilities of transformations by layered networks, statistical neurodynamics, the dynamical characteristics of associative memory, a general theory of neural learning, and self-organization of neural networks.
- OSTI ID:
- 6357408
- Journal Information:
- Proceedings of the IEEE (Institute of Electrical and Electronics Engineers); (USA), Vol. 78:9; ISSN 0018-9219
- Country of Publication:
- United States
- Language:
- English
Similar Records
A simple VLSI architecture for neurocomputing
1991 IEEE International Joint Conference on Neural Networks, Singapore, Nov. 18-21, 1991, Proceedings. Vols. 1-3
Multistage neural network model for dynamic scene analysis
Conference
·
Thu Sep 01 00:00:00 EDT 1988
· Neural Networks; (United States)
·
OSTI ID:6357408
+1 more
1991 IEEE International Joint Conference on Neural Networks, Singapore, Nov. 18-21, 1991, Proceedings. Vols. 1-3
Conference
·
Tue Jan 01 00:00:00 EST 1991
·
OSTI ID:6357408
Multistage neural network model for dynamic scene analysis
Miscellaneous
·
Sun Jan 01 00:00:00 EST 1989
·
OSTI ID:6357408