Ideomotor feedback control in a recurrent neural network

2014/02/14 by Mathieu Galtier, Galtier, Mathieu
Biochemistry, Genetics and Molecular Biology · Computer Science · Neuroscience · Physics and Astronomy · #Adaptation and Self-Organizing Systems (nlin.AO) #FOS: Biological sciences #FOS: Physical sciences #Neural Networks and Applications #Neural Networks and Reservoir Computing #Neural dynamics and brain function #Neurons and Cognition (q-bio.NC) #nlin.AO #q-bio.NC

paper · pdf · doi:10.48550/arxiv.1402.3563

openalex publication_date 2014/02/14 · arxiv created 2015/01/18 · arxiv updated 2015/01/20 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

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.

Citations

• A hierarchical neural-network model for control and learning of voluntary movement
• Identification and control of dynamical systems using neural networks

Related

• Recurrent Control Nets for Deep Reinforcement Learning
• Learning Dynamics of RNNs in Closed-Loop Environments
• Exploring Deep and Recurrent Architectures for Optimal Control
• Neural network learning of optimal Kalman prediction and control
• A neural network model for timing control with reinforcement