Performance of Activation Functions Used in Recurrent Neural Networks

摘要：

According to the conventional gradient algorithm, a type of gradient-based neural networks (GNN) is developed and presented for the online solution of the constant Lyapunov matrix equation. For the superior convergence, such GNN models is improved and investigated by adding different types activation functions. Theoretical and simulative results both substantiate the efficacy of the improved neural networks for Lyapunov matrix equation soiling.

关键词： Recurrent neural networks Lyapunov matrix equation Activation function Global exponential convergence

作者: Chenfu Yi Yuhuan Chen

作者单位: School of Information Engineering Jiangxi University of Science and Technology Ganzhou 341000,China Center for Educational Technology Gannan Normal University Ganzhou 341000,China

会议类型: 国际会议

会议名称: 2011 3rd International Conference on Computer and Network Technology(ICCNT 2011)(2011第三届IEEE计算机与网络技术国际会议)

会议地点: 太原

会议语种:英文

页码: 40-43

在线出版日期: 2011-02-26（万方平台首次上网日期，不代表论文的发表时间）