Abstract— Neural processing of large-scale data sets containing both many input / output variables and a large number of training examples often leads to very large networks. Onc...
In this paper, we propose a novel method which involves neural adaptive techniques for identifying salient features and for classifying high dimensionality data. In particular a ne...
A training data selection method for multi-class data is proposed. This method can be used for multilayer neural networks (MLNN). The MLNN can be applied to pattern classification...
Abstract. In many supervised learning tasks it can be costly or infeasible to obtain objective, reliable labels. We may, however, be able to obtain a large number of subjective, po...
This paper presents a neural network approach to the problem of nding the dialogue act for a given utterance. So far only symbolic, decision tree and statistical approaches were ut...