Ghent University Academic Bibliography

Advanced

Unsupervised learning in reservoir computing: modeling hippocampal place cells for small mobile robots

Eric Antonelo UGent and Benjamin Schrauwen UGent (2009) LECTURE NOTES IN COMPUTER SCIENCE. 5768. p.747-756
abstract
Biological systems (e.g., rats) have efficient and robust localization abilities provided by the so called, place cells, which are found in the hippocampus of rodents and primates (these cells encode locations of the animal's environment). This work seeks to model these place cells by employing three (biologically plausible) techniques: Reservoir Computing (RC), Slow Feature Analysis (SFA), and Independent Component Analysis (ICA). The proposed architecture is composed of three layers, where the bottom layer is a dynamic reservoir of recurrent nodes with fixed weights. The upper layers (SFA and ICA) provides a self-organized formation of place cells, learned in a unsupervised way. Experiments show that a simulated mobile robot with 17 noisy short-range distance sensors is able to self-localize in its environment with the proposed architecture, forming a spatial representation which is dependent on the robot direction.
Please use this url to cite or link to this publication:
author
organization
year
type
conference
publication status
published
subject
keyword
robot localization, place cells, reservoir computing, neural networks
in
LECTURE NOTES IN COMPUTER SCIENCE
Lect. Notes Comput. Sci.
editor
Cesare Alippi, Marios Polycarpou, Christos Panayiotou and Georgios Ellinas
volume
5768
issue title
Artificial Neural Networks – ICANN 2009
pages
747 - 756
publisher
Springer
place of publication
Berlin, Germany
conference name
19th International Conference on Artificial Neural Networks (ICANN)
conference location
Limassol, Cyprus
conference start
2009-09-14
conference end
2009-09-17
Web of Science type
Proceedings Paper
Web of Science id
000275896600077
ISSN
1611-3349
0302-9743
ISBN
978-3-642-04273-7
DOI
10.1007/978-3-642-04274-4_77
language
English
UGent publication?
yes
classification
P1
copyright statement
I have transferred the copyright for this publication to the publisher
id
726906
handle
http://hdl.handle.net/1854/LU-726906
date created
2009-08-13 11:49:25
date last changed
2010-08-04 13:52:21
@inproceedings{726906,
  abstract     = {Biological systems (e.g., rats) have efficient and robust localization abilities provided by the so called, place cells, which are found in the hippocampus of rodents and primates (these cells encode locations of the animal's environment). This work seeks to model these place cells by employing three (biologically plausible) techniques: Reservoir Computing (RC), Slow Feature Analysis (SFA), and Independent Component Analysis (ICA). The proposed architecture is composed of three layers, where the bottom layer is a dynamic reservoir of recurrent nodes with fixed weights. The upper layers (SFA and ICA) provides a self-organized formation of place cells, learned in a unsupervised way. Experiments show that a simulated mobile robot with 17 noisy short-range distance sensors is able to self-localize in its environment with the proposed architecture, forming a spatial representation which is dependent on the robot direction.},
  author       = {Antonelo, Eric and Schrauwen, Benjamin},
  booktitle    = {LECTURE NOTES IN COMPUTER SCIENCE},
  editor       = {Alippi, Cesare and Polycarpou, Marios and Panayiotou, Christos and Ellinas, Georgios},
  isbn         = {978-3-642-04273-7},
  issn         = {1611-3349},
  keyword      = {robot localization,place cells,reservoir computing,neural networks},
  language     = {eng},
  location     = {Limassol, Cyprus},
  pages        = {747--756},
  publisher    = {Springer},
  title        = {Unsupervised learning in reservoir computing: modeling hippocampal place cells for small mobile robots},
  url          = {http://dx.doi.org/10.1007/978-3-642-04274-4\_77},
  volume       = {5768},
  year         = {2009},
}

Chicago
Antonelo, Eric, and Benjamin Schrauwen. 2009. “Unsupervised Learning in Reservoir Computing: Modeling Hippocampal Place Cells for Small Mobile Robots.” In Lecture Notes in Computer Science, ed. Cesare Alippi, Marios Polycarpou, Christos Panayiotou, and Georgios Ellinas, 5768:747–756. Berlin, Germany: Springer.
APA
Antonelo, E., & Schrauwen, B. (2009). Unsupervised learning in reservoir computing: modeling hippocampal place cells for small mobile robots. In C. Alippi, M. Polycarpou, C. Panayiotou, & G. Ellinas (Eds.), LECTURE NOTES IN COMPUTER SCIENCE (Vol. 5768, pp. 747–756). Presented at the 19th International Conference on Artificial Neural Networks (ICANN), Berlin, Germany: Springer.
Vancouver
1.
Antonelo E, Schrauwen B. Unsupervised learning in reservoir computing: modeling hippocampal place cells for small mobile robots. In: Alippi C, Polycarpou M, Panayiotou C, Ellinas G, editors. LECTURE NOTES IN COMPUTER SCIENCE. Berlin, Germany: Springer; 2009. p. 747–56.
MLA
Antonelo, Eric, and Benjamin Schrauwen. “Unsupervised Learning in Reservoir Computing: Modeling Hippocampal Place Cells for Small Mobile Robots.” Lecture Notes in Computer Science. Ed. Cesare Alippi et al. Vol. 5768. Berlin, Germany: Springer, 2009. 747–756. Print.