In this paper, a new algorithm for blind inversion of Wiener systems is presented. The algorithm is based on minimization of mutual information of the output samples. This minimiz...
A crucial problem in non-linear time series forecasting is to determine its auto-regressive order, in particular when the prediction method is non-linear. We show in this paper tha...
Recently, a real-time clustering microchip based on the ART1 algorithm has been reported. That chip was able to classify 100-bit input patterns into up to 18 categories. However, i...
A new model which can recognize rotated, distorted, scaled, shifted and noised patterns is proposed. The model is constructed based on psychological experiments in a mental rotatio...
This paper presents results from lesion experiments on a modular attractor neural network model of semantic access. Real picture data forms the basis of perceptual input to the mod...
William Power, Ray J. Frank, D. John Done, Neil Da...
Abstract: Support vector machines (SVMs) are primarily designed for 2-class classification problems. Although in several papers it is mentioned that the combination of K SVMs can b...
To avoid the curse of dimensionality, function approximators are used in reinforcement learning to learn value functions for individual states. In order to make better use of comp...
This paper describes the use of Simple HTML Ontology Extensions (SHOE) in a real world internet application. SHOE allows authors to add semantic content to web pages and to relate...
Abstract. We examine the effects of changing the coefficient of variation (CV) of the inter-stimulus interval on the CV of the output interspike interval (ISI), using constant magn...