MOSAIC model for sensorimotor learning and control

DOI10.1162/089976601750541778MaRDI QIDQ2762421zbMATH OpenOpenAlexWikidataFDO

Authors Masahiko Haruno, Daniel M. Wolpert, Mitsuo Kawato

Publication date 12 May 2002

Published in Neural Computation (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1162/089976601750541778

zbMATH Keywords

modular selection and identification for controlMOSAIC architecture

Mathematics Subject Classification ID

Theory of languages and software systems (knowledge-based systems, expert systems, etc.) for artificial intelligence (68T35)

Recommendations

• An Internal Model for Acquisition and Retention of Motor Learning During Arm Reaching
• MOSAIC for multiple-reward environments
• Modelling of direct motor program learning in fast human arm motions
• Online learning and control of attraction basins for the development of sensorimotor control strategies
• A novel model of motor learning capable of developing an optimal movement control law online from scratch

Cites work

• A Maximization Technique Occurring in the Statistical Analysis of Probabilistic Functions of Markov Chains
• Adaptive control using multiple models
• On-line estimation of hidden Markov model parameters based on the Kullback-Leibler information measure

Cited in

(27)

• From motor to sensory processing in mirror neuron computational modelling
• The emergence of movement units through learning with noisy efferent signals and delayed sensory feedback
• Incremental acquisition of multiple nonlinear forward models based on differentiation process of schema model
• From internal models toward metacognitive AI
• A model for the transfer of control from the brain to the spinal cord through synaptic learning
• Online learning and control of attraction basins for the development of sensorimotor control strategies
• Bipedal locomotion: toward unified concepts in robotics and neuroscience
• Learning flexible sensori-motor mappings in a complex network
• Extraction of primitive representation from captured human movements and measured ground reaction force to generate physically consistent imitated behaviors
• Mirror neurons and imitation: a computationally guided review
• A probabilistic model of gaze imitation and shared attention
• MOSAIC for multiple-reward environments
• Closed-loop deep learning: generating forward models with backpropagation
• An Internal Model for Acquisition and Retention of Motor Learning During Arm Reaching
• Sensitivity Derivatives for Flexible Sensorimotor Learning
• The modular modality frame model: continuous body state estimation and plausibility-weighted information fusion
• Isotropic Sequence Order Learning
• ISO Learning Approximates a Solution to the Inverse-Controller Problem in an Unsupervised Behavioral Paradigm
• Dynamics model abstraction scheme using radial basis functions
• Multiple Model-Based Reinforcement Learning
• Space-Efficient Euler Partition and Bipartite Edge Coloring
• Polyhedral mixture of linear experts for many-to-one mapping inversion and multiple controllers
• Reward prediction errors, not sensory prediction errors, play a major role in model selection in human reinforcement learning
• Closed-loop and open-loop control of posture and movement during human trunk bending
• Modeling of autonomous problem solving process by dynamic construction of task models in multiple tasks environment
• Heterarchical reinforcement-learning model for integration of multiple cortico-striatal loops: fMRI examination in stimulus-action-reward association learning
• The emergence of goals in a self-organizing network: a non-mentalist model of intentional actions

This page was built for publication: MOSAIC model for sensorimotor learning and control

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2762421)