神经元的集聚原理与智能子波神经网络  

Principle of Neurons Assemblage and Intelligent Wavelet Neural Network

作　　者：张山[1] 周凤岐[1] 

机构地区：[1]西北工业大学航天工程学院,西安710071

出　　处：《系统工程与电子技术》1999年第9期61-64,共4页Systems Engineering and Electronics

基　　金：航空科学基金资助课题

摘　　要：在对神经元机能空间分布结构和状态转换深入研究的基础上，提出了神经元的集聚原理，并通过构造一种基于广义子波基函数的神经元积聚模型，讨论了由此实现的智能子波神经网络所具有的广义结构可调和广义信息记忆等智能化特性。最后，通过两个仿真实验验证了新网络模型在有关实际问题解决上的可行性和高效性。In this paper, based on the thorough research on the space structure of functional distribution and the change of states of neurons, the principle of neurons assemblage is presented. Through the construction of an intelligent neurons assemblage model with generalized wavelet basis function as its excited function,the intelligent characters of the intelligent waveletd neural network, such as the generalized adjustment of structure and generalized information storing, are thend icussed. Finally, the feasibility and efficiency on solving the concerned problems are verified by two simulations.

关 键 词：神经元 算法 模型 人工神经网络 

分 类 号：TP18[自动化与计算机技术—控制理论与控制工程]