结构自适应自组织神经网络的研究

A Study on Structural Adapting SelfOrganizing Neural Network

针对Ｋｏｈｏｎｅｎ的自组织特征映射（ＳＯＦＭ）神经网络的不足，本文把进化计算的思想用于神经网络的结构寻优之中，提出了一种结构自适应的自组织神经网络（ＳＡＳＯＮＮ）模型．ＳＡＳＯＮＮ基于把每个神经元看成是一个进化群体中的一个个体的观点，构造了神经元生长（ｇｒｏｗｉｎｇ）和删除（ｐｒｕｎｉｎｇ）的准则和方法，使得ＳＯＦＭ中的神经元欠利用，神经网络映射欠准确。

A new structural adapting selforganizing network model SASONN,which can be thought as an extension of Kohonen's SOFM,is presented in this paper.We proved that,if each neuron in the network have equal winning frequency in stationary status,the density of neuron is proportional of the p.d.f of sample set instead of its 2/3 power.The essence of evolutionary commputing is introduced to network optimization.We treat each neuron as individual of the evolutionary population and construct rules of neuron growing and pruning.Some deffects in SOFM,such as incorrect mapping,neuron underuse and boundary effect can be overcomed in SASONN.