Title :
A New MNN´s Training Method with Empirical Study
Author :
Jiasen Wang ; Pan Wang
Abstract :
Based on the thought of “to be expert in one aspect and good at many”, a new training method of modular neural network (MNN) is presented. The key point of this method is a subnet learns the neighbor data sets while fulfiling its main task : learning the objective data set. Both methodology and empirical study of this new method are presented. Two examples (static approximation and nonlinear dynamic system prediction) are tested to show the new method´s effectiveness: average testing error is dramatically decreased compared to original algorithm..
Keywords :
approximation theory; learning (artificial intelligence); neural nets; MNN training method; average testing error; ensemble learning; modular neural network method; neighbor data sets; nonlinear dynamic system prediction; static approximation; Clustering algorithms; Multi-layer neural network; Sociology; Statistics; Testing; Training; Ensemble learning; Modular Neural Network; Performance analysis; To be expert in one aspect and good at many;
Conference_Titel :
Intelligent Systems (GCIS), 2012 Third Global Congress on
Conference_Location :
Wuhan
Print_ISBN :
978-1-4673-3072-5
DOI :
10.1109/GCIS.2012.35
