A Cortico-Cerebellar Model That Learns to Generate Distributed Motor Commands to Control a Kinematic Arm
Abstract
A neurophysiologically-based model is presented that controls a simulated kinematic arm during goal-directed reaches. The network generates a quasi-feedforward motor command that is learned using training signals generated by corrective movements. For each target, the network selects and sets the output of a subset of pattern generators. During the move(cid:173) ment, feedback from proprioceptors turns off the pattern generators. The task facing individual pattern generators is to recognize when the arm reaches the target and to turn off. A distributed representation of the mo(cid:173) tor command that resembles population vectors seen in vivo was produced naturally by these simulations.
Cite
Text
Berthier et al. "A Cortico-Cerebellar Model That Learns to Generate Distributed Motor Commands to Control a Kinematic Arm." Neural Information Processing Systems, 1991.Markdown
[Berthier et al. "A Cortico-Cerebellar Model That Learns to Generate Distributed Motor Commands to Control a Kinematic Arm." Neural Information Processing Systems, 1991.](https://mlanthology.org/neurips/1991/berthier1991neurips-corticocerebellar/)BibTeX
@inproceedings{berthier1991neurips-corticocerebellar,
title = {{A Cortico-Cerebellar Model That Learns to Generate Distributed Motor Commands to Control a Kinematic Arm}},
author = {Berthier, N. E. and Singh, S. P. and Barto, A. G. and Houk, J. C.},
booktitle = {Neural Information Processing Systems},
year = {1991},
pages = {611-618},
url = {https://mlanthology.org/neurips/1991/berthier1991neurips-corticocerebellar/}
}