Physical Sciences and Mathematics Commons^™

An Efficient Neural Algorithm For The Multiclass Problem, Rangachari Anand, Kishan Mehrotra, Chilukuri K. Mohan, Sanjay Ranka

Electrical Engineering and Computer Science - Technical Reports

One connectionist approach to the classification problem, which has gained popularity in recent years, is the use of backpropagation-trained feed-forward neural networks. In practice, however, we find that the rate of convergence of net output error is especially low when training networks for multi-class problems. In this paper, we show that while backpropagation will reduce the Euclidean distance between the actual and desired output vectors, the difference between some of the components of these vectors will actually increase in the first iteration. Furthermore, the magnitudes of subsequent weight changes in each iteration are very small, so that many iterations are …