论文信息 - Evaluation and improvement of two training algorithms

Evaluation and improvement of two training algorithms

Two effective neural network training algorithms are output weight optimization - hidden weight optimization and conjugate gradient. The former performs better on correlated data, and the latter performs better on random data. Based on these observations and others, we develop a procedure to test general neural network training algorithms. Since good neural network algorithm should perform well for all kinds of data, we develop alternation algorithms, which have runs of the different algorithms in turn. The alternation algorithm works well for both kinds of data.

Jiang Li | Tae-Hoon Kim | M.T. Manry

[1] Mu-Song Chen,et al. Constructive proof of efficient pattern storage in the multi-layer perceptron , 1993, Proceedings of 27th Asilomar Conference on Signals, Systems and Computers.

[2] Farid U. Dowla,et al. Ship wake-detection procedure using conjugate gradient trained artificial neural networks , 1991, IEEE Trans. Geosci. Remote. Sens..

[3] Michael T. Manry,et al. Cramer Rao Maximum A-Posteriori Bounds on Neural Network Training Error for Non-Gaussian Signals and Parameters , 1996 .

[4] Etienne Barnard,et al. Optimization for training neural nets , 1992, IEEE Trans. Neural Networks.

[5] Michael T. Manry,et al. A neural network training algorithm utilizing multiple sets of linear equations , 1996, Conference Record of The Thirtieth Asilomar Conference on Signals, Systems and Computers.

[6] C. Charalambous,et al. Conjugate gradient algorithm for efficient training of artifi-cial neural networks , 1990 .

[7] Farid U. Dowla,et al. Backpropagation Learning for Multilayer Feed-Forward Neural Networks Using the Conjugate Gradient Method , 1991, Int. J. Neural Syst..