KLUEDO RSS FeedKLUEDO Dokumente/documents
https://kluedo.ub.uni-kl.de/index/index/
Mon, 03 Apr 2000 00:00:00 +0200Mon, 03 Apr 2000 00:00:00 +0200Existence and Learning of Oscillations in Recurrent Neural Networks
https://kluedo.ub.uni-kl.de/frontdoor/index/index/docId/641
In this paper we study a particular class of \(n\)-node recurrent neural networks (RNNs).In the \(3\)-node case we use monotone dynamical systems theory to show,for a well-defined set of parameters, that,generically, every orbit of the RNN is asymptotic to a periodic orbit.Then, within the usual 'learning' context of NeuralNetworks, we investigate whether RNNs of this class can adapt their internal parameters soas to 'learn' and then replicate autonomously certain external periodic signals.Our learning algorithm is similar to identification algorithms in adaptivecontrol theory. The main feature of the adaptation algorithm is that global exponential convergenceof parameters is guaranteed. We also obtain partial convergence results in the \(n\)-node case. Stuart Townley; Achim Ilchmann; Martin G. Weiß; Warren McClements; Antonio C. Ruiz; David H. Owens; Dieter Prätzel-Wolterspreprinthttps://kluedo.ub.uni-kl.de/frontdoor/index/index/docId/641Mon, 03 Apr 2000 00:00:00 +0200