원문정보
보안공학연구지원센터(IJGDC)
International Journal of Grid and Distributed Computing
Vol.8 No.1
2015.02
pp.159-168
피인용수 : 0건 (자료제공 : 네이버학술정보)
초록
영어
A novel chaotic-neuron model is presented by introducing the non-monotonous activation function which is composed of the Legendre function and the Sigmoid function. The reversed bifurcation of the chaotic neuron model is given and analyzed, meanwhile, how do parameters influence the network convergence speed is discussed. Based on the neuron model, the piecewise simulated annealing SLF chaotic neural network was made by introducing the simulated annealing idea, the model improve the convergence speed, at the same time, the precision of this network have not being influenced. The simulation experiment of function optimization and TSP problem verify the effectiveness of the segmented simulated annealing strategy.
목차
Abstract
1. Introduction
2. SLF Chaotic Neuron Model and the Impact of Parameter
2.1. SLF Chaotic Neurons Model
2.2. Effects of Combination Parameters on the Convergence Rate
2.3. Effects of Annealing Parameters on the Convergence Rate
3. SLF Chaonic Network Model with Piecewise Simulated Annealing Strategy
4. The Applications of SLF Chaotic Neural Network with Piecewise Simulated Annealing Strategy
4.1. Application of Model in Function Optimization
4.2. Application of Model in Combination Optimization (TSP)
5. Conclusion
References
1. Introduction
2. SLF Chaotic Neuron Model and the Impact of Parameter
2.1. SLF Chaotic Neurons Model
2.2. Effects of Combination Parameters on the Convergence Rate
2.3. Effects of Annealing Parameters on the Convergence Rate
3. SLF Chaonic Network Model with Piecewise Simulated Annealing Strategy
4. The Applications of SLF Chaotic Neural Network with Piecewise Simulated Annealing Strategy
4.1. Application of Model in Function Optimization
4.2. Application of Model in Combination Optimization (TSP)
5. Conclusion
References
저자정보
참고문헌
자료제공 : 네이버학술정보