Optimization by neural networks
- 1 January 1988
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 1, 325-332 vol.2
- https://doi.org/10.1109/icnn.1988.23944
Abstract
The ability to map and solve a number of interesting problems on neural networks motivates a proposal for using neural networks as a highly parallel model for general-purpose computing. The author review this proposal, showing how to map combinational optimization problems, including graph K-partitioning, vertex cover, maximum independent set, maximum clique, number partitioning, and maximum matching. They report that performance results are quite encouraging; the solutions for graph partitioning and task allocation problems are comparable to those obtained using heuristics and the running times are significantly lower than those required using simulated annealing.Keywords
This publication has 8 references indexed in Scilit:
- Simulated Annealing: Theory and ApplicationsPublished by Springer Nature ,1987
- Computing with Neural Circuits: A ModelScience, 1986
- Parallel Distributed ProcessingPublished by MIT Press ,1986
- “Neural” computation of decisions in optimization problemsBiological Cybernetics, 1985
- Neurons with graded response have collective computational properties like those of two-state neurons.Proceedings of the National Academy of Sciences, 1984
- Optimization by Simulated AnnealingScience, 1983
- Data Structures and Network AlgorithmsPublished by Society for Industrial & Applied Mathematics (SIAM) ,1983
- Neural networks and physical systems with emergent collective computational abilities.Proceedings of the National Academy of Sciences, 1982