A differential Hebbian framework for biologically-plausible motor control

DOI10.1016/j.neunet.2022.03.002zbMath1525.93121arXiv2006.13471OpenAlexW3212945014MaRDI QIDQ6072576

Sergio Verduzco-Flores, Erik De Schutter, William Dorrell

Publication date: 13 October 2023

Published in: Neural Networks (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/2006.13471

zbMATH Keywords

feedback controlreinforcement learningmotor controlsynaptic plasticity

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Feedback control (93B52) Neural networks for/in biological studies, artificial life and related topics (92B20) Multivariable systems, multidimensional control systems (93C35) Linear systems in control theory (93C05)

Cites Work

• Unnamed Item
• Unnamed Item
• Mathematical properties of neuronal TD-rules and differential Hebbian learning: a comparison
• A control design method for a class of switched linear systems
• Simple statistical gradient-following algorithms for connectionist reinforcement learning
• A stable added-mass partitioned (AMP) algorithm for elastic solids and incompressible flow
• Forward models for physiological motor control
• MOSAIC for Multiple-Reward Environments
• Learning Curves for Stochastic Gradient Descent in Linear Feedforward Networks
• Sensitivity Derivatives for Flexible Sensorimotor Learning
• On the Asymptotic Equivalence Between Differential Hebbian and Temporal Difference Learning
• ISO Learning Approximates a Solution to the Inverse-Controller Problem in an Unsupervised Behavioral Paradigm
• Wavelet transforms versus Fourier transforms
• NEURAL EXCITABILITY, SPIKING AND BURSTING
• Strongly Improved Stability and Faster Convergence of Temporal Sequence Learning by Using Input Correlations Only