广义知识存储原理与高阶广义神经网络

Generalized Information Storing Principle and Higher-Order Generalized Neural Networks

本文在仔细分析神经网络知识存储方式的基础止，提出了高阶广义神经网络的概念和构成原则，讨论了其中一种典型的智能神经元模型以及据此实现的高阶广义神经网络的各项性能，最后将其与标准的ＢＰ算法进行了比较。

Based on analysis about neural networks' information storing principle,the concept and principle of higher-order generalized neural networks are proposed,of which a typical intelligent neuron model and the characteristics of corresponding higher-order generalized neural networks are disscussed and also compared with standard BP algorithm.