A new learning algorithm with reference-following variables

• 作 者: BaiquanLUE YuanCAO
• 机 构: DeparmaentofAutomation
• 出 处: 控制理论与应用：英文版
• 发表日期: 2004年4期
• 关键词: 神经网络 收敛理论 学习算法 拓扑结构 Neural networks Convergence theory BP learning method Ref
• 基金项目: 上海市教育基金

A learning algorithm is presented for the learning of neural networks,in which the learning trajectory is convergence without any over-learning by changing of topological construction of the algorithm near any local minimum points of learning error.Becaus