Ghent University Academic Bibliography

Advanced

A discrete/rhythmic pattern generating RNN

Tim Waegeman UGent, Francis wyffels UGent and Benjamin Schrauwen UGent (2012) Proceedings of the 20th European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning. p.567-572
abstract
Biological research supports the concept that advanced motion emerges from modular building blocks, which generate both rhythmical and discrete patterns. Inspired by these ideas, roboticists try to implement such building blocks using different techniques. In this paper, we show how to build such module by using a recurrent neural network (RNN) to encapsulate both discrete and rhythmical motion patterns into a single network. We evaluate the proposed system on a planar robotic manipulator. For training, we record several handwriting motions by back driving the robot manipulator. Finally, we demonstrate the ability to learn multiple motions (even discrete and rhythmic) and evaluate the pattern generation robustness in the presence of perturbations.
Please use this url to cite or link to this publication:
author
organization
year
type
conference
publication status
published
subject
keyword
Robot Arm, Reservoir Computing, Neural Network
in
Proceedings of the 20th European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning
editor
Michel Verleysen
pages
567 - 572
publisher
Ciaco - i6doc.com
place of publication
Louvain-la-Neuve, Belgium
conference name
20th European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning (ESANN - 2012)
conference location
Bruges, Belgium
conference start
2012-04-25
conference end
2012-04-27
ISBN
9782874190476
language
English
UGent publication?
yes
classification
C1
copyright statement
I have transferred the copyright for this publication to the publisher
id
2105908
handle
http://hdl.handle.net/1854/LU-2105908
date created
2012-05-14 13:29:59
date last changed
2012-05-16 12:37:53
@inproceedings{2105908,
  abstract     = {Biological research supports the concept that advanced motion emerges from modular building blocks, which generate both rhythmical and discrete patterns. Inspired by these ideas, roboticists try to implement such building blocks using different techniques. In this paper, we show how to build such module by using a recurrent neural network (RNN) to encapsulate both discrete and rhythmical motion patterns into a single network. We evaluate the proposed system on a planar robotic manipulator. For training, we record several handwriting motions by back driving the robot manipulator. Finally, we demonstrate the ability to learn multiple motions (even discrete and rhythmic) and evaluate the pattern generation robustness in the presence of perturbations.},
  author       = {Waegeman, Tim and wyffels, Francis and Schrauwen, Benjamin},
  booktitle    = {Proceedings of the 20th European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning},
  editor       = {Verleysen, Michel},
  isbn         = {9782874190476},
  keyword      = {Robot Arm,Reservoir Computing,Neural Network},
  language     = {eng},
  location     = {Bruges, Belgium},
  pages        = {567--572},
  publisher    = {Ciaco - i6doc.com},
  title        = {A discrete/rhythmic pattern generating RNN},
  year         = {2012},
}

Chicago
Waegeman, Tim, Francis wyffels, and Benjamin Schrauwen. 2012. “A Discrete/rhythmic Pattern Generating RNN.” In Proceedings of the 20th European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning, ed. Michel Verleysen, 567–572. Louvain-la-Neuve, Belgium: Ciaco - i6doc.com.
APA
Waegeman, T., wyffels, F., & Schrauwen, B. (2012). A discrete/rhythmic pattern generating RNN. In M. Verleysen (Ed.), Proceedings of the 20th European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning (pp. 567–572). Presented at the 20th European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning (ESANN - 2012), Louvain-la-Neuve, Belgium: Ciaco - i6doc.com.
Vancouver
1.
Waegeman T, wyffels F, Schrauwen B. A discrete/rhythmic pattern generating RNN. In: Verleysen M, editor. Proceedings of the 20th European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning. Louvain-la-Neuve, Belgium: Ciaco - i6doc.com; 2012. p. 567–72.
MLA
Waegeman, Tim, Francis wyffels, and Benjamin Schrauwen. “A Discrete/rhythmic Pattern Generating RNN.” Proceedings of the 20th European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning. Ed. Michel Verleysen. Louvain-la-Neuve, Belgium: Ciaco - i6doc.com, 2012. 567–572. Print.