State prediction: a constructive method to program recurrent neural networks

Authors:
René Felix Reinhart;Jochen Jakob Steil
Affiliations:
Research Institute for Cognition and Robotics Lab. & Faculty of Technology, Bielefeld University, Bielefeld, Germany;Research Institute for Cognition and Robotics Lab. & Faculty of Technology, Bielefeld University, Bielefeld, Germany
Venue:
ICANN'11 Proceedings of the 21th international conference on Artificial neural networks - Volume Part I
Year:
2011

Citing 3
Cited 0

On the dynamics of small continuous-time recurrent neural networks

Adaptive Behavior - Special issue on computational neuroethology
Input space bifurcation manifolds of recurrent neural networks

Neurocomputing
New results on recurrent network training: unifying the algorithms and accelerating convergence

IEEE Transactions on Neural Networks

Quantified Score

Hi-index	0.00

Visualization

Abstract

We introduce a novel technique to program desired state sequences into recurrent neural networks in one shot. The basic methodology and its scalability to large and input-driven networks is demonstrated by shaping attractor landscapes, transient dynamics and programming limit cycles. The approach unifies programming of transient and attractor dynamics in a generic framework.