具线性可分训练样本时在线BP神经网络的有限收敛性

Finite Convergence of On-line BP Neural Networks with Linearly Separable Training Patterns

中文关键词:  非线性前馈神经网络  在线BP算法  有限收敛性  线性可分训练样本.

英文关键词:nonlinear feedforward neural networks  online BP algorithms  finite convergence  linearly separable training patterns.

中文摘要:

      当训练样本线性可分时,本文证明前馈神经网络的在线BP算法是有限次收敛的.

英文摘要:

      In this paper we prove a finite convergence of online BP algorithms for nonlinear feedforward neural networks when the training patterns are linearly separable.