Optimal solutions for cellular neural networks by paralleled hardware annealing
- 1 March 1996
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Neural Networks
- Vol. 7 (2) , 440-454
- https://doi.org/10.1109/72.485679
Abstract
An engineering annealing method for optimal solutions of cellular neural networks is presented. Cellular neural networks are very promising in solving many scientific problems in image processing, pattern recognition, and optimization by the use of stored program with predetermined templates. Hardware annealing, which is a paralleled version of mean-field annealing in analog networks, is a highly efficient method of finding optimal solutions of cellular neural networks. It does not require any stochastic procedure and henceforth can be very fast. The generalized energy function of the network is first increased by reducing the voltage gain of each neuron. Then, the hardware annealing searches for the globally minimum energy state by continuously increasing the gain of neurons. The process of global optimization by the proposed annealing can be described by the eigenvalue problems in the time-varying dynamic system. In typical nonoptimization problems, it also provides enough stimulation to frozen neurons caused by ill-conditioned initial states.Keywords
This publication has 25 references indexed in Scilit:
- Paralleled hardware annealing for optimal solutions on electronic neural networksIEEE Transactions on Neural Networks, 1993
- Genetic algorithm for CNN template learningIEEE Transactions on Circuits and Systems I: Regular Papers, 1993
- Design of linear cellular neural networks for motion sensitive filteringIEEE Transactions on Circuits and Systems II: Analog and Digital Signal Processing, 1993
- A current-mode cellular neural network implementationIEEE Transactions on Circuits and Systems II: Analog and Digital Signal Processing, 1993
- Current-mode techniques for the implementation of continuous- and discrete-time cellular neural networksIEEE Transactions on Circuits and Systems II: Analog and Digital Signal Processing, 1993
- Resistive grid image filtering: input/output analysis via the CNN frameworkIEEE Transactions on Circuits and Systems I: Regular Papers, 1992
- A CNN chip for connected component detectionIEEE Transactions on Circuits and Systems, 1991
- Image thinning with a cellular neural networkIEEE Transactions on Circuits and Systems, 1990
- Nonlinear switched capacitor 'neural' networks for optimization problemsIEEE Transactions on Circuits and Systems, 1990
- Optimization by Simulated AnnealingScience, 1983