摘要
本文首先研究完全连接型高阶神经网络的逼近能力，并证明了定义在｛０，１｝＾Ｎ上的任意布尔函数都可以由完全连接的高阶神经网络来实现。接着提出了旨在简化网络结构的去除冗余连接权删减算法，并用于高阶神经分类器的稀疏化实现。模拟实验结果证明了这种算法的有效性。
In this paper, the fully-connected higher-order neuron and sparsed higher-order neuron are introduced, the mapping capabilities of the fully-connected higher-order neural networks are investigated, and that arbitrary Boolean function defined from {0,1}N can be realized by fully-connected higher-order neural networks is proved. Based on this, in order to simplify the networks' architecture, a pruning algorithm for eliminating the redundant connection weights is also proposed, which can be applied to the implementation of sparsed higher-order neural classifier. The simulated results show the effectiveness of the algorithm.
关键词
高阶神经网络
冗余连接权
稀疏化连接
删减算法
Higher-order neural networks, Redundant connection weights, Sparsed connection, Pruning algorithm
