Open AccessADAPTIVE TRAINING AND PRUNING FOR NEURAL NETWORKS:ALGORITHMS AND APPLICATION
Author(s) -
Shu Chen,
Shengjiang Chang,
Jing Yuan,
Yanxin Zhang,
Kwok Wo Wong
Publication year - 2001
Publication title -
wuli xuebao
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.199
H-Index - 47
ISSN - 1000-3290
DOI - 10.7498/aps.50.674
Subject(s) - computer science , pruning , extended kalman filter , artificial neural network , algorithm , pace , training (meteorology) , artificial intelligence , function (biology) , covariance matrix , machine learning , kalman filter , physics , evolutionary biology , meteorology , agronomy , biology , geodesy , geography
Finding an optimal network size is one of the major concerns when building a neural network. In using the local extended Kalman filter (EKF) algorithm, we propose an efficient approach that combines EKF training and pruning as a whole. In particular, the covariance matrix obtained along with the local EKF training can be utilized to indicate the importance of the network weights. As a result, the network size can be determined adaptively to keep pace with the changes in input characteristics. The effectiveness of this algorithm is demonstrated on generalized XOR logic function and handwritten digit recognition.