智能控制与相对熵最小化

Intelligrnt Control with Relative Entropy Minimizing

中文关键词  智能控制  相对熵  IPDI原理  学习功能  记忆功能  归纳功能

英文关键词  intelligent control  relative entropy  principle of IPDI  function of learning  function of assaciative memory  function of induction

中文摘要

      根据神经行为学和认知心理学观点提出智能控制系统的新构型，从相对熵最小化原理构建智能控制理论。从神经生理学和神经网络理论证明分层控制系统的基本原理IPDI（Increasing ptrcision with decreasing intelligence）,从相对熵最小化观点和IPDI原理出发，讨论智能系统的智能行为，给出关于智能系统学习过程的几个定理和学习算法。

英文摘要

      Based on the point of view of neuroethology and cognition-psychology,a new configuration of intelligent control system is presented in this paper;the theory of intelligent control is constrol is constructed by principle of minimizing of relstvie entropy.The baduc principle of hierarchical intelligent control(IPDI-Increasing precising precision wuth decreasing intelligence)is probed from points of the neutophysiology and the theory of neural network.Intelligent system is discussed from the viewpoint of minimzing of relative entropy and from the prinple of IPDI;several theorems and algorithms for the learning process of intelligent system are given in this paper.