New Training Method and Optimal Structure of Backpropagation Networks

• Published in: Advances in Natural Computation pp. 157 - 166
• Main Authors: Sureerattanan, Songyot, Sureerattanan, Nidapan
• Format: Book Chapter Conference Proceeding
• Language: English
• Published: Berlin, Heidelberg Springer Berlin Heidelberg 2005; Springer
• Series: Lecture Notes in Computer Science
• Subjects: Akaike Information Criterion; Applied sciences; Artificial intelligence; Computer science; control theory; systems; Computer systems and distributed systems. User interface; Exact sciences and technology; Hide Layer; Kalman Filter; Mean Square Error; Output Layer; Software; Bayes estimation; Conjugate gradient method; Backpropagation; Backpropagation algorithm; Kalman filter; Linear filter; Bayes network; Nonlinear problems; Neural network; Market price; Convergence speed
• ISBN: 3540283234; 9783540283232
• ISSN: 0302-9743; 1611-3349
• DOI: 10.1007/11539087_18

New algorithm was devised to speed up the convergence of backpropagation networks and the Bayesian Information Criterion was presented to obtain the optimal network structure. Nonlinear neural network problem can be partitioned into the nonlinear part in the weights of the hidden layers and the linear part in the weights of the output layer. We proposed the algorithm for speeding up the convergence by employing the conjugate gradient method for the nonlinear part and the Kalman filter algorithm for the linear part. From simulation experiments with daily data on the stock prices in the Thai market, it was found that the algorithm and the Bayesian Information Criterion could perform satisfactorily.