: We present a symbol recognition method without segmentation of the document. Our approach uses Zernike moments for the coding and a multilayered Perceptron for the classifier. Re...
An efficient algorithm to train general differential recurrent neural networks is proposed. The trained network can be directly used as the internal model of a predictive controll...
In this paper we present the design and evaluation of intrusion detection models for MANETs using supervised classification algorithms. Specifically, we evaluate the performance of...
In this paper, approximation by linear combinations of an increasing number n of computational units with adjustable parameters (such as perceptrons and radial basis functions) is ...
Sets of multivariable functions are described for which worst case errors in linear approximation are larger than those in approximation by neural networks. A theoretical framework...