Internal Models as Echo State Networks : Learning to Execute Arm Movements
As robots are becoming more and more complex, with higher degrees-of-freedom, lighter limbs, and springy joints, it becomes harder to control their movements. New approaches, inspired from neuroscience, are attracting increased attention among computer scientists dealing with motor control. The focu...
Main Author: | Løvlid, Rikke Amilde |
---|---|
Format: | Doctoral Thesis |
Language: | English |
Published: |
Norges teknisk-naturvitenskapelige universitet, Institutt for datateknikk og informasjonsvitenskap
2013
|
Online Access: | http://urn.kb.se/resolve?urn=urn:nbn:no:ntnu:diva-23554 http://nbn-resolving.de/urn:isbn:978-82-471-4810-5 (printed ver.) http://nbn-resolving.de/urn:isbn:978-82-471-4811-2 (electronic ver.) |
Similar Items
-
Tailoring Echo State Networks for Optimal Learning
by: Pau Vilimelis Aceituno, et al.
Published: (2020-09-01) -
Transferring learning from external to internal weights in echo-state networks with sparse connectivity.
by: David Sussillo, et al.
Published: (2012-01-01) -
Hippocampus as an Echo State Network
by: Mutalik, Prabhanjan
Published: (2018) -
Restricted Kinematics in Children With Autism in the Execution of Complex Oscillatory Arm Movements
by: Hu, X., et al.
Published: (2021) -
Evolving Echo State Networks for Minimally Cognitive Unsupervised Learning Tasks
by: Stuan, Dag
Published: (2013)