Computing with structured neural networks
- 1 March 1988
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in Computer
- Vol. 21 (3) , 91-103
- https://doi.org/10.1109/2.34
Abstract
The authors are concerned with how one can design, realize, and analyze networks that embody the specific computational structures needed to solve hard problems. They focus on the design and use of massively parallel connectionist computational models, particularly in artificial intelligence. They describe a computing environment for working with structured networks and present some sample applications. Throughout, they treat adaptation and learning as ways to improve structured networks, not as replacements for analysis and design.Keywords
This publication has 5 references indexed in Scilit:
- Connectionist learning proceduresArtificial Intelligence, 1989
- Computing motion using analog and binary resistive networksComputer, 1988
- Computing with structured connectionist networksCommunications of the ACM, 1988
- Computing with Neural Circuits: A ModelScience, 1986
- Dynamic connections in neural networksBiological Cybernetics, 1982