Computing with structured neural networks
Recent work on neural network computation, much of it carried out by physicists, examines the emergent behavior of large, unstructured collections of computing units. The authors are more concerned with how one can design, realize, and analyze networks that embody the specific computational structures needed to solve hard problems. In this article the authors focus on the design and use of massively parallel computational models, particularly in artificial intelligence. They also describe a computing environment for working with structured networks and present some sample applications. Throughout, the authors treat adaptation and learning as ways to improve structured networks, not as replacements for analysis and design.
- Research Organization:
- Univ. of Rochester (US)
- OSTI ID:
- 5369787
- Journal Information:
- Computer; (United States), Journal Name: Computer; (United States) Vol. 21:3; ISSN CPTRB
- Country of Publication:
- United States
- Language:
- English
Similar Records
Computing with structured connections networks. Technical report
Neural Networks
Schemas and neural networks for sixth generation computing
Technical Report
·
Tue Mar 31 23:00:00 EST 1987
·
OSTI ID:5255449
Neural Networks
Technical Report
·
Tue Sep 23 00:00:00 EDT 2003
·
OSTI ID:815740
Schemas and neural networks for sixth generation computing
Journal Article
·
Fri Mar 31 23:00:00 EST 1989
· Journal of Parallel and Distributed Computing; (USA)
·
OSTI ID:5345778