摘要
提出了一种新的用粒子群优化RBF网络学习的算法,即分组训练合成优化。该算法利用粒子之间的合作与竞争以实现对多维复杂空间的高维搜索能力,找出神经网络权值的最优解,以达到优化神经网络学习的目的。通过与用最小二乘法优化的神经网络进行了比较,结果表明算法所优化的神经网络收敛效果明显、收敛速度快。
A RBP neural network learning algorithm based on particle swarm optimizers（PSO）, that is grouping training and composing optimizer, is proposed in this paper. The optimizer realizes multi - dimension searching ability to multi - dimension complex space for the best weight of neural network . At last, through the comparison of least square method, the result shows that it is good in speed.
出处
《计算机技术与发展》
2006年第2期185-187,共3页
Computer Technology and Development
