Modeling and control of nonlinear complex system by fusion of control theory and learning network

点击翻译按钮获取中文摘要

To model and control the nonlinear complex system, it is very useful to research the function of the human brain and learning method of the living things. Under these considerations, we mainly developed,i) an indirect encoding method with genetic algorithm to decide an optimal neural network structure,ii) a method for faster neural networks learning to make a neural network control system,iii) a control system structure to makes the system robust by using the second order derivatives of universal learning network,iv) an effective reinforcement learning method with an adaptively modified probabilistic density function to make the agents adaptable to the environment,v) an useful method for chaotic neural network to associate the memory patterns in the case that each memory patterns have strong correlation each other,vi) a memory search model with association by features in chaotic neural network which makes system enable a quick association.These validity has been examined by examples.