BIOMAT Database Logo BIOMAT Database Logo

Existence and learning of oscillations in recurrent neural networks. 2000

S Townley, and A Ilchmann, and M G Weiss, and W McClements, and A C Ruiz, and D H Owens, and D Pratzel-Wolters
School of Mathematical Sciences, University of Exeter, Exeter EX4 4QE, UK.

In this paper we study a particular class of -node recurrent neural networks (RNN's). 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 we investigate whether RNN's of this class can adapt their internal parameters so as to "learn" and then replicate autonomously (in feedback) certain external periodic signals. Our learning algorithm is similar to identification algorithms in adaptive control theory. The main feature of the algorithm is that global exponential convergence of parameters is guaranteed. We also obtain partial convergence results in the -node case.

UI MeSH Term Description Entries

Related Publications

S Townley, and A Ilchmann, and M G Weiss, and W McClements, and A C Ruiz, and D H Owens, and D Pratzel-Wolters
Existence, learning, and replication of periodic motions in recurrent neural networks.
January 1998, IEEE transactions on neural networks,
S Townley, and A Ilchmann, and M G Weiss, and W McClements, and A C Ruiz, and D H Owens, and D Pratzel-Wolters
Noise induced oscillations in recurrent neural networks.
January 2009, Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference,
S Townley, and A Ilchmann, and M G Weiss, and W McClements, and A C Ruiz, and D H Owens, and D Pratzel-Wolters
Learning spiking neuronal networks with artificial neural networks: neural oscillations.
April 2024, Journal of mathematical biology,
S Townley, and A Ilchmann, and M G Weiss, and W McClements, and A C Ruiz, and D H Owens, and D Pratzel-Wolters
Stimulus statistics shape oscillations in nonlinear recurrent neural networks.
February 2015, The Journal of neuroscience : the official journal of the Society for Neuroscience,
S Townley, and A Ilchmann, and M G Weiss, and W McClements, and A C Ruiz, and D H Owens, and D Pratzel-Wolters
Inaccessibility in online learning of recurrent neural networks.
October 2004, Physical review letters,
S Townley, and A Ilchmann, and M G Weiss, and W McClements, and A C Ruiz, and D H Owens, and D Pratzel-Wolters
Hebbian learning of context in recurrent neural networks.
November 1996, Neural computation,
S Townley, and A Ilchmann, and M G Weiss, and W McClements, and A C Ruiz, and D H Owens, and D Pratzel-Wolters
Quantum recurrent neural networks for sequential learning.
September 2023, Neural networks : the official journal of the International Neural Network Society,
S Townley, and A Ilchmann, and M G Weiss, and W McClements, and A C Ruiz, and D H Owens, and D Pratzel-Wolters
Effective learning in recurrent max-min neural networks.
April 1998, Neural networks : the official journal of the International Neural Network Society,
S Townley, and A Ilchmann, and M G Weiss, and W McClements, and A C Ruiz, and D H Owens, and D Pratzel-Wolters
Stable dynamic backpropagation learning in recurrent neural networks.
January 1999, IEEE transactions on neural networks,
S Townley, and A Ilchmann, and M G Weiss, and W McClements, and A C Ruiz, and D H Owens, and D Pratzel-Wolters
Learning Long Temporal Sequences in Spiking Networks by Multiplexing Neural Oscillations.
January 2020, Frontiers in computational neuroscience,
Copied contents to your clipboard!