Adaptive algorithm for training pRAM neural networks on unbalanced data sets

作     者：Ramanan, S Clarkson, TG Taylor, JG 

作者机构：Univ Essex Dept Elect Syst Engn Colchester CO4 3SQ Essex England Univ London Kings Coll Dept Elect & Elect Engn London WC2R 2LS England Univ London Kings Coll Dept Math London WC2R 2LS England 

出 版 物：《ELECTRONICS LETTERS》 (电子学快报)

年 卷 期：1998年第34卷第13期

页      面：1335-1336页

核心收录：

学科分类：0808[工学-电气工程] 0809[工学-电子科学与技术（可授工学、理学学位）] 08[工学] 

主　　题：pyrimidal pRAM neural networks learning (artificial intelligence) Neural nets adaptive learning rate algorithm Adaptive system theory a priori class probability standard reinforcement learning algorithm unbalanced data sets feedforward neural nets 

摘      要：A novel algorithm for training pyramidal pRAM neural networks on an unbalanced training set is proposed. The behaviour of the standard reinforcement learning algorithm is analysed and an adaptive learning rate algorithm that modifies the reinforcement learning algorithm based on readily available a priori class probability is developed.