节点文献
BP网络激励函数的研究
Studies on the activation functions of BP algorithm
【摘要】 研究BP算法中激励函数f对收敛速度的影响 ,并将其用于传感器静态误差的综合修正 ,实验证明取得了较好的效果 ,得出了陡峭函数收敛快的结论
【Abstract】 The influence of activation functions in BP algorithms is studied,and we come to a conclusion: The more cliffy the function is, the quicker the convergence of the algorithm , then applied this method in correcting the quiet error of the sensor, it proves that the result is effective to improve the perform of BP network.
【关键词】 神经网络;
BP算法;
激励函数;
局部极小;
梯度下降法;
【Key words】 neural networks; BP algorithm; activation function; local minimum; gradient method;
【Key words】 neural networks; BP algorithm; activation function; local minimum; gradient method;
- 【文献出处】 苏州大学学报(自然科学) ,JOURNAL OF SUZHOU UNIVERSITY , 编辑部邮箱 ,2002年04期
- 【分类号】TP183
- 【被引频次】47
- 【下载频次】235