HALF OF THRESHOLD ALGORITHM: AN ENHANCED LINEAR ADAPTIVE SKIPPING TRAINING ALGORITHM OR MULTILAYER FEEDFORWARD NEURAL NETWORKS
Manjula Devi Ramasamy and Kuppuswami Subbaraya Gounder
DOI : 10.3844/ajassp.2014.38.46
American Journal of Applied Sciences
Volume 11, Issue 1
Multilayer Feed Forward Neural Network (MFNN) has been successfully administered architectures for solving a wide range of supervised pattern recognition tasks. The most problematic task of MFNN is training phase which consumes very long training time on very huge training datasets. An enhanced linear adaptive skipping training algorithm for MFNN called Half of Threshold (HOT) is proposed in this research paper. The core idea of this study is to reduce the training time through random presentation of training input samples without affecting the network’s accuracy. The random presentation is done by partitioning the training dataset into two distinct classes, classified and misclassified class, based on the comparison result of the calculated error measure with half of threshold value. Only the input samples in the misclassified class are presented to the next epoch for training, whereas the correctly classified class is skipped linearly which dynamically reducing the number of input samples exhibited at every single epoch without affecting the network’s accuracy. Thus decreasing the size of the training dataset linearly can reduce the total training time, thereby speeding up the training process. This HOT algorithm can be implemented with any training algorithm used for supervised pattern classification and its implementation is very simple and easy. Simulation study results proved that HOT training algorithm achieves faster training than the other standard training algorithm.
© 2014 Manjula Devi Ramasamy and Kuppuswami Subbaraya Gounder. This is an open access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.