作者: G. Auda , M. Kamel
DOI: 10.1109/IJCNN.1998.685972
关键词: Modular neural network 、 Time delay neural network 、 Voting 、 Artificial neural network 、 Computer science 、 Artificial intelligence
摘要: Cooperation by voting is one of the popular modular neural network decision-making strategies. Ensemble classifiers are multiple identical modules which use for post-learning classification. This paper suggests a new cooperation scheme ensembles utilizes in learning process itself. According to suggested scheme, different would, automatically, focus on regions input space. Hence, temporal crosstalk decreases and decision boundaries drawn accurately complex overlapping