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
Journal ArticleDOI
Control of a recurrent neural network emulator for the double scroll
TL;DR: In this paper, a recurrent neural network that behaves as the double scroll is stabilized and controlled by means of linear dynamic feedback, and the controller design is based upon stability criteria for neural control systems and involves the solution of a nonlinear optimization problem.
State equations of nonlinear dynamic systems
TL;DR: It is shown that this formulation can be written in a closed form (namely a descriptor form which lies close to the state space formulation), E:_ x I (t) = A:x I ( t) + B:u(t) + G:_ u(t), with E, A, B and G ex-plicitely depending on some bond graph eld matrices.
Journal ArticleDOI
CNN Algorithms for Video Authentication and Copyright Protection
TL;DR: The implementation of an image comparison algorithm and cryptographic hash functions on the regular array of cellular neural network cells are described, necessary for message authentication and copyright protection in the multimedia service environment.
Book ChapterDOI
Collisions for Schnorr's Hash Function FFT-Hash Presented at Crypto '91
TL;DR: A method is described to generate collisions for the hash function FFT-Hash that was presented by Claus Schnorr at Crypto '91 and a set of colliding messages is given that was obtained.