Sliding Mode Algorithm for Online Learning in Analog Multilayer Feedforward Neural Networks
Sliding Mode Algorithm for Online Learning in Analog Multilayer Feedforward Neural Networks
复制标题
模拟多层前馈神经网络在线学习的滑模算法
DOI：
10.1007/3-540-44989-2_127
复制
发表时间：
2003
期刊：
影响因子：
--
通讯作者：
O. Kaynak
中科院分区：
文献类型：
--
作者：
N. Shakev;A. Topalov;O. Kaynak
针对标量输出模拟多层前馈网络的自适应学习问题，提出了一种新的动态滑模控制算法。这类神经结构被广泛应用于非线性动态系统的建模、辨识和控制。将学习误差变量的零水平集视为网络学习参数空间中的滑动面。证明了算法的收敛性质，并给出了算法收敛的条件。将其应用于两层前馈神经网络的非单调函数在线学习，取得了较好的效果。
A new dynamical sliding mode control algorithm is proposed for robust adaptive learning in analog multilayer feedforward networks with a scalar output. These type neural structures are widely used for modeling, identification and control of nonlinear dynamical systems. The zero level set of the learning error variable is considered as a sliding surface in the space of network learning parameters. The convergence of the algorithm is established and conditions are given. Its effectiveness is shown when applied to on-line learning of nonmonotonic function using a two-layered feedforward neural network.