论文信息 - Novel fast training algorithm for multilayer feedforward neural network

Novel fast training algorithm for multilayer feedforward neural network

A new fast learning algorithm for a multilayer feedforward neural network is presented. The new algorithm, based on an innovative variable step size and gradient averaging, has excellent properties to overcome major drawbacks of the backpropagation algorithm and shows high convergence speed. The improved performance of new algorithm in comparison with other algorithms is verified via computer simulations.< >

Dong-Jo Park | Jung-Hoon Kim | Byung-Eul Jun

[1] Robert A. Jacobs,et al. Increased rates of convergence through learning rate adaptation , 1987, Neural Networks.

[2] Geoffrey E. Hinton,et al. Learning internal representations by error propagation , 1986 .

[3] Richard P. Lippmann,et al. An introduction to computing with neural nets , 1987 .

[4] John J. Shynk,et al. Performance surfaces of a single-layer perceptron , 1990, IEEE Trans. Neural Networks.