Sciweavers

Share
IWANN
1999
Springer
9 years 8 months ago
Blind Inversion of Wiener Systems
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...
Anisse Taleb, Jordi Solé i Casals, Christia...
IWANN
1999
Springer
9 years 8 months ago
Forecasting Financial Time Series through Intrinsic Dimension Estimation and Non-Linear Data Projection
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...
Michel Verleysen, Eric de Bodt, Amaury Lendasse
IWANN
1999
Springer
9 years 8 months ago
Adaptive Resonance Theory Microchips
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...
Teresa Serrano-Gotarredona, Bernabé Linares...
IWANN
1999
Springer
9 years 8 months ago
Pattern Recognition System with Top-Down Process of Mental Rotation
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...
Shunji Satoh, Hirotomo Aso, Shogo Miyake, Jousuke ...
IWANN
1999
Springer
9 years 8 months ago
A Modular Attractor Model of Semantic Access
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...
IWANN
1999
Springer
9 years 8 months ago
Support Vector Machines for Multi-class Classification
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...
Eddy Mayoraz, Ethem Alpaydin
IWANN
1999
Springer
9 years 8 months ago
Using Temporal Neighborhoods to Adapt Function Approximators in Reinforcement Learning
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...
R. Matthew Kretchmar, Charles W. Anderson
IWANN
1999
Springer
9 years 8 months ago
Applying Ontology to the Web: A Case Study
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...
Jeff Heflin, James A. Hendler, Sean Luke
IWANN
1999
Springer
9 years 8 months ago
Paradoxical Relationship between Output and Input Regularity for the FitzHugh-Nagumo Model
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...
Stuart Feerick, Jianfeng Feng, David Brown
books