EBP based GK-LM Method For Neural Network Training

摘要：

In this paper we proposed a new algorithm for neural network training. This algorithm is developed from modification on Levenberg-Marquardt algorithm for MLP neural network learning. The proposed algorithm has good convergence. This method reduces the amount of oscillation in learning procedure. We named this algorithm as GK-LM Method. An example is given here to show usefulness of this method. Finally a simulation verifies the results of proposed method.

关键词： GK-LM Method modification neural network Variable learning rate

作者: Kethepalli Malllikarjuna G.R.C.Kaladhara Sarma M.V.Subramanyam K.Satya Prasad

作者单位: Dept. of ECE,RGMCET NANDYAL Dept. of EIE,RGMCET ,NAND YAL Principal ,SREC NANDYAL Ret, JNTUK NANDYAL

会议类型: 国际会议

会议名称: 2011 3rd IEEE International Conference on Computer Research and Development(ICCRD 2011)(2011第三届计算机研究与发展国际会议)

会议地点: 上海

会议语种:英文

页码: 504-507

在线出版日期: 2011-03-11（万方平台首次上网日期，不代表论文的发表时间）