基于熵的自组织神经网络树

神经网络由于优越的学习和分类能力已被用于许多模式识别的问题，并取得了很好的结果。但是对于识别大样本集和复杂模式的问题，绝大多数常规的神经网络在决定网络的结构和规模以及应付庞大的计算量等方面有着种种困难。为了克服这些困难，文中提出一种基于条件类别熵的结构自适应的神经网络树；这种神经网络树由具有拓扑有序特性的子网络组成，而树的规模由条件类别熵决定。它的主要优点是对于识别大样本集和复杂模式的问题能够通过结构自适应自动地确定网络的结构和规模。实验显示这种神经网络树对于识别大样本集和复杂模式是非常有效的。

A Self-Organizing Neural Network Tree Base on Entropy

Neural network have been successfully applied to various pattern classification problem in term of their learning ability and high discrimination power. However, for the case of classifying large set and complex patterns, the greater part of conventional neural networks suffer from several difficulties such as the determination of the structure and size of the network, the computational complexity, and so on. To cope with these difficulties, this paper proposes a s tructurally adaptive intelligent neural tree based on conditional class entropy. The basic idea is to partition hierarchically input space using a tree structural network, which is composed of subnetworks with topology-preserving mapping ability. The structure and size of the network is determined by conditional class entropy. The main advantage of the neural tree is that it attempts to find automatically a network structure and size suitable for classification of large set and complex patterns through structure adaptation. Experimental results show that this neur al tree is very effective for classification of large set and complex patterns.