Title :
A novel hysteretic neural network and its application
Author_Institution :
Coll. of Autom., Harbin Eng. Univ., Harbin, China
Abstract :
To improve the optimization performance of hysteretic chaotic neural networks, a hysteretic chaotic neural network with the properties of characterizing local detailed features and stochastic chaotic simulated annealing (SCSA) is proposed. A hysteretic activation function, which can provide hysteretic dynamics for neural networks, is composed of two offset sigmoid activation functions. The exponentially decaying dilation parameter in wavelet is used for chaotic simulated annealing, and the stochastically varying translation parameter in wavelet is used to construct stochastic simulated annealing. Phenomena of chaos and hysteresis make the network escape from local minima, while the properties of SCSA and the local characterizing ability of wavelet make the network contribute to improving the probability of finding the global minima. The experimental results show that it has a higher probability to obtaining a global optimization solution.
Keywords :
chaos; neural nets; simulated annealing; stochastic processes; wavelet transforms; decaying dilation parameter; hysteretic chaotic neural network; stochastic chaotic simulated annealing; stochastically varying translation parameter; wavelet tranformation; Artificial neural networks; Automation; Chaos; Educational institutions; Gaussian processes; Hysteresis; Neural networks; Neurons; Simulated annealing; Stochastic processes; Chaos; Hysteresis; Neural network; Traveling salesman problem; Wavelet;
Conference_Titel :
Information and Automation (ICIA), 2010 IEEE International Conference on
Conference_Location :
Harbin
Print_ISBN :
978-1-4244-5701-4
DOI :
10.1109/ICINFA.2010.5512250