论文部分内容阅读
提出了一种新的训练多层神经网络的适应性共轭梯度学习算法。理论分析和仿真结果证明 ,它在模式识别领域里是—种可行和有效的算法 ,而且其识别能力优于传统的BP算法 ,收敛速度也比BP算法快
A new adaptive conjugate gradient learning algorithm for training multi-layer neural networks is proposed. Theoretical analysis and simulation results show that it is a feasible and effective algorithm in the field of pattern recognition, and its recognition ability is superior to the traditional BP algorithm, the convergence speed is faster than the BP algorithm