基于超立方体覆盖的构造性网络学习算法  

Constructive training algorithm based on hypercube covering

作　　者：谌卫军[1] 林福宗[1] 李建民[1] 张钹[1] 

机构地区：[1]清华大学计算机科学与技术系智能技术与系统国家重点实验室,北京100084

出　　处：《清华大学学报（自然科学版）》2003年第1期97-100,共4页Journal of Tsinghua University(Science and Technology)

基　　金：国家自然科学基金重点资助项目(60135010);国家"九七三"重点基础研究资助项目(G1998030509)

摘　　要：该文提出了一种基于超立方体覆盖的构造性神经网络学习算法,以解决二值型输入变量的K分类问题。该算法分两步来动态地构造一个三层前馈网络。首先,对于每一类的所有训练样本,用尽可能少的超立方体来覆盖它们,并为每一个超立方体构造一个隐层单元;其次,用"或"操作把这些隐单元连接到相应的输出单元上。文章给出了相应的理论分析和一个具体的实现。实验结果表明,该算法优于常用的一些归纳学习算法。A constructive training algorithm based on hypercube covering was developed for classification problems involving binaryvalued input attributes and multiple output classes. The algorithm dynamically constructs a threelayer feedforward neural network in two stages. First, for all the training examples in each class, the algorithm finds a set of hypercubes to cover the examples with each hypercube corresponding to a hidden neuron. Then, these neurons are connected to the corresponding output unit using the OR operation. The algorithm is analyzed theoretically and illustrated by an example. The results show that the method is superior to other commonly used inductive algorithms.

关 键 词：构造性网络学习算法 人工神经网络 构造法 超立方体覆盖 BP算法 K分类 二值型输入变量 

分 类 号：TP183[自动化与计算机技术—控制理论与控制工程]