关键词: 二元蚁群算法, 前馈神经网络, 拥挤交通组织, 反向传播算法, 函数逼近

Abstract: Multi-layer feedforward neural network based on binary ant colony algorithms is designed.At the same time the crowded traffic organization tactics is introduced to avoid the convergence to the local minimum points.The combination of binary colony algorithms with the neural network can have both extensive mapping ability of neural network and rapid global convergence ability of binary ant colony algorithms.The result shows better by the example of function approaching.

Key words: binary ant colony algorithms, feedforward neural network, crowded traffic organization tactics, back-propagation, function approaching