蚁群算法优化前向神经网络的一种方法

The Optimization of Feed-Forward Neural Networks Based on Ant Colony Algorithm

蚁群算法(ACA)是一种新型的寻优策略,此文章尝试将蚁群算法用于三层前向神经网络的学习过程,建立了相应的优化模型,进行了实际的编程计算,并与加动量项的BP算法、演化算法以及模拟退火算法进行比较,结果表明ACA具有更好的全局收敛性,鲁棒性强,以及对初值不敏感等特点。

Ant Colony Algorithm（ACA） is a novel optimizing method proposed lately.An Ant Colony Algorithm（ACA） for the optimization of feed-forward neural networks and a model based on this method are presented in this paper, Compared with the Back-propagation Algorithm added momentum,the evolutionary Algorithm and the Simulated Annealing Algorithm,optimization result of feed-forward neural networks by ACA demonstrates that ACA has a strong robustness and good global astringency.It also shows that ACA is insensitive to initial values.