Ideomotor feedback control in a recurrent neural network

DOI10.1007/S00422-015-0648-4MaRDI QIDQ309520zbMATH OpenOpenAlexDBLPWikidataFDO

Authors Mathieu N. Galtier

Publication date 7 September 2016

Published in Biological Cybernetics (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/1402.3563

zbMATH Keywords

feedback controlrecurrent neural networkecho state networkrecursive least squares

Mathematics Subject Classification ID

Neural networks for/in biological studies, artificial life and related topics (92B20) Feedback control (93B52)

Abstract: The architecture of a neural network controlling an unknown environment is presented. It is based on a randomly connected recurrent neural network from which both perception and action are simultaneously read and fed back. There are two concurrent learning rules implementing a sort of ideomotor control: (i) perception is learned along the principle that the network should predict reliably its incoming stimuli; (ii) action is learned along the principle that the prediction of the network should match a target time series. The coherent behavior of the neural network in its environment is a consequence of the interaction between the two principles. Numerical simulations show the promising performance of the approach, which can be turned into a local, and thus "biologically plausible", algorithm.

Recommendations

• Neural network learning of optimal Kalman prediction and control
• scientific article; zbMATH DE number 64900
• Resonant spatiotemporal learning in large random recurrent networks
• Learning combined feedback and feedforward control of a musculoskeletal system
• Control of the behavior of objects in the exterior medium and possibilities of neural network solutions

Cites work

• scientific article; zbMATH DE number 5719294 (Why is no real title available?)
• scientific article; zbMATH DE number 3670263 (Why is no real title available?)
• scientific article; zbMATH DE number 53595 (Why is no real title available?)
• scientific article; zbMATH DE number 3435336 (Why is no real title available?)
• scientific article; zbMATH DE number 804845 (Why is no real title available?)
• A hierarchical neural-network model for control and learning of voluntary movement
• Every good regulator of a system must be a model of that system †
• Mathematical formulations of Hebbian learning
• On stability of switched linear systems with perturbed switching paths
• Optimization and applications of echo state networks with leaky- integrator neurons
• Order of N complexity transform domain adaptive filters
• Strong instability of solitary-wave solutions for a nonlinear Boussinesq equation

Cited in

(5)

• Template-Based Approach to Resolve Redundancies in Motor Control
• Distributed adaptive control: A proposal on the neuronal organization of adaptive goal oriented behavior
• Fuzzy neuronal model of motor control inspired by cerebellar pathways to online and gradually learn inverse biomechanical functions in the presence of delay
• Neural network learning of optimal Kalman prediction and control
• A differential Hebbian framework for biologically-plausible motor control

This page was built for publication: Ideomotor feedback control in a recurrent neural network

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q309520)