基于蚁群算法的二进神经网络学习算法

An ant colony-based learning algorithm for binary neural networks

本文提出一种实现任意布尔函数的二进神经网络学习算法,该算法首先借助蚁群算法优化选择核心节点及节点访问顺序;其次,根据优化的节点访问顺序给出扩张分类超平面的步骤,减少了隐层神经元的数目,同时给出隐层神经元及输出元的表达形式;并进一步通过理论分析了该算法的收敛性。该算法成功地改进了已有学习算法的不足,并通过典型实例验证了该算法的有效性。

This paper presents a learning algorithm to realize any Boolean function for binary neural networks. In this paper, by means of the ant colony algorithm, we obtain the optimized core nodes and the extension order of true nodes, so this algorithm can reduce the number of hidden neurons in network, and the expression of the hidden neurons and the output neuron are also given. Furthermore, we analyze the convergence of this algorithm. This algorithm improves the deficiency of existing algorithms successfully, and these advantages are verified by basic numerical experiments.