TY - INPR
A1 - Townley, Stuart
A1 - Ilchmann, Achim
A1 - Weiß, Martin G.
A1 - McClements, Warren
A1 - Ruiz, Antonio C.
A1 - Owens, David H.
A1 - Prätzel-Wolters, Dieter
T1 - Existence and Learning of Oscillations in Recurrent Neural Networks
N2 - 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.
T3 - Berichte der Arbeitsgruppe Technomathematik (AGTM Report) - 202
KW - Recurrent neural networks
KW - Learning systems
KW - Nonlinear dynamics
KW - Monotone dynamical systems
Y1 - 1998
UR - https://kluedo.ub.uni-kl.de/frontdoor/index/index/docId/641
UR - https://nbn-resolving.org/urn:nbn:de:hbz:386-kluedo-6107
ER -