Structure Perturbation Optimization for Hopfield-Type Neural Networks
In this paper, we extract the core idea of state perturbation from Hopfield-type neural networks and define state perturbation formulas to describe the general way of optimization methods. Departing from the core idea and the formulas, we propose a novel optimization method related to neural network structure, named structure perturbation optimization. Our method can produce a structure transforming process to retrain Hopfield-type neural networks to get better problem-solving ability. Experiments validate that our method effectively helps Hopfield-type neural networks to escape from local minima and get superior solutions.
Keywordsstochastic noise structure perturbation Hopfield-type neural network maximum clique problem
Unable to display preview. Download preview PDF.
- 2.Van Den, D.E., Miller III, T.K.: Improving the Performance of the Hopfield-Tank Neural Network Through Normalization and Annealing. Biol. Cybern. 139, 129–139 (1989)Google Scholar
- 5.He, Y.Y.: Chaotic Simulated Annealing with Decaying Chaotic Noise. IEEE Trans. Neural Netw. 13(6), 1526–1531 (2002)Google Scholar
- 6.Chen, S.S.: Chaotic simulated annealing by a neural network with a variable delay: design and application. IEEE Trans. Neural Netw. 22(10), 1557–1565 (2011)Google Scholar
- 8.Sun, M., Zhao, L., Cao, W., Xu, Y.Q., Dai, X.F., Wang, X.X.: Novel hysteretic noisy chaotic neural network for broadcast scheduling problems in packet radio networks. IEEE Trans. Neural Netw. 21(9), 1422–1433 (2010)Google Scholar