Title :
EBP based GK-LM method for neural network training
Author :
Malllikarjuna, Kethepalli ; Sarma, G. R C Kaladhara ; Subramanyam, M.V. ; Prasad, K. Satya
Author_Institution :
Dept. of ECE, RGMCET, Nandyal, India
Abstract :
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.
Keywords :
backpropagation; multilayer perceptrons; GK-LM Method; Levenberg-Marquardt algorithm; MLP neural network learning; convergence; error back propagation; learning procedure; oscillation; Algorithm design and analysis; Artificial neural networks; Jacobian matrices; Joints; Oscillators; Training; GK-LM Method; Variable learning rate; modification; neural network;
Conference_Titel :
Computer Research and Development (ICCRD), 2011 3rd International Conference on
Conference_Location :
Shanghai
Print_ISBN :
978-1-61284-839-6
DOI :
10.1109/ICCRD.2011.5764184
