A sensitivity-based training algorithm with architecture adjusting for madalines

How to design proper architectures of neural networks for solving given problems is an important issue in neural network research. Nowadays, the existing training algorithms of neural networks only focus on adjusting neural networks´ weights to improve training accuracy, and few of them adaptively adjust the networks´ architecture. However, the architecture is indeed very critical for training neural networks to have high performance and needs to be coped with in the training process. In this paper, we present a new training algorithm of Madalines, which takes not only weight but also architecture adjusting into consideration. The algorithm can thus train Madalines with smaller architecture and higher generalization ability. Experimental results have demonstrated that our algorithm is effective.