Optimization using neural networks
- 1 January 1991
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Computers
- Vol. 40 (12) , 1347-1358
- https://doi.org/10.1109/12.106220
Abstract
The design of feedback (or recurrent) neural networks to produce good solutions to complex optimization problems is discussed. The theoretical basis for applying neural networks to optimization problems is reviewed, and a design rule that serves as a primitive for constructing a wide class of constraints is introduced. The use of the design rule is illustrated by developing a neural network for producing high-quality solutions to a probabilistic resource allocation task. The resulting neural network has been simulated on a high-performance parallel processor that has been optimized for neural network simulation.Keywords
This publication has 25 references indexed in Scilit:
- A hierarchical multiple-view approach to three-dimensional object recognitionIEEE Transactions on Neural Networks, 1991
- A novel objective function for improved phoneme recognition using time-delay neural networksIEEE Transactions on Neural Networks, 1990
- Identification and control of dynamical systems using neural networksIEEE Transactions on Neural Networks, 1990
- Neuromorphic electronic systemsProceedings of the IEEE, 1990
- 30 years of adaptive neural networks: perceptron, Madaline, and backpropagationProceedings of the IEEE, 1990
- A Near-Optimum Parallel Planarization AlgorithmScience, 1989
- Nonlinear neural networks: Principles, mechanisms, and architecturesNeural Networks, 1988
- Computing with Neural Circuits: A ModelScience, 1986
- Simple 'neural' optimization networks: An A/D converter, signal decision circuit, and a linear programming circuitIEEE Transactions on Circuits and Systems, 1986
- Learning Process in an Asymmetric Threshold NetworkPublished by Springer Nature ,1986