J
Joos Vandewalle
Researcher at Katholieke Universiteit Leuven
Publications - 747
Citations - 42250
Joos Vandewalle is an academic researcher from Katholieke Universiteit Leuven. The author has contributed to research in topics: Artificial neural network & Singular value decomposition. The author has an hindex of 73, co-authored 747 publications receiving 39621 citations. Previous affiliations of Joos Vandewalle include University of Virginia & Catholic University of Leuven.
Papers
More filters
Book
Cellular Neural Networks, Multi-Scroll Chaos and Synchronization
TL;DR: Cellular Neural/Nonlinear Networks Multi-Scroll Chaotic and Hyperchaotic Attractors Synchronization of Chaotic Lur'e Systems Engineering Applications.
Journal ArticleDOI
Training multilayer perceptron classifiers based on a modified support vector method
TL;DR: A training method for one hidden layer multilayer perceptron classifier which is based on the idea of support vector machines (SVM's) and an upper bound on the Vapnik-Chervonenkis dimension is iteratively minimized over the interconnection matrix of the hidden layer and its bias vector.
Journal ArticleDOI
Reducing the Number of Support Vectors of SVM Classifiers Using the Smoothed Separable Case Approximation
TL;DR: An algorithm is proposed, called the smoothed SCA (SSCA), that additionally upper-bounds the weight vector of the pruned solution and, for the commonly used kernels, reduces the number of support vectors even more.
Journal ArticleDOI
An efficient microcode compiler for application specific DSP processors
TL;DR: A computer program for microcode compilation for custom digital signal processors is presented, part of the CATHEDRAL II silicon compiler, which allows for the automatic synthesis of processor architectures which simultaneously exploit pipelining and parallelism.
Journal ArticleDOI
Nonlinear system identification using neural state space models, applicable to robust control design
TL;DR: A linear fractional transformation representation is given for neural state space models, which makes it possible to use these models, obtained from input/output measurements on a plant, in a standard robust performance control scheme.