Experiments with Reservoir Computing on the road sign problem

Reference : Experiments with Reservoir Computing on the road sign problem


	Document type :	Scientific congresses, symposiums and conference proceedings : Paper published in a book
	Discipline(s) :	Engineering, computing & technology : Computer science
	To cite this reference:	http://hdl.handle.net/10993/36481

Title :	Experiments with Reservoir Computing on the road sign problem
Language :	English
Author, co-author :	Antonelo, Eric Aislan [University of Luxembourg > Interdisciplinary Centre for Security, Reliability and Trust (SNT) >]
	Schrauwen, Benjamin [> >]
	Stroobandt, Dirk [> >]
Publication date :	2007
Main document title :	Proceedings of the VIII Brazilian Congress on Neural Networks (CBRN)
Peer reviewed :	Yes
Audience :	International
Event name :	VIII Brazilian Congress on Neural Networks (CBRN)
Event date :	Oct 2007
Abstract :	[en] The road sign problem is tackled in this work with Reservoir Computing (RC) networks. These networks are made of a fixed recurrent neural network where only a readout layer is trained. In the road sign problem, an agent has to decide at some point in time which action to take given relevant information gathered in the past. We show that RC can handle simple and complex T-maze tasks (which are a subdomain of the road sign problem).
Permalink :	http://hdl.handle.net/10993/36481
DOI :	10.21528/CBRN2007-047
Other URL :	http://abricom.org.br/eventos/cbrn_2007/50100047-2/

File(s) associated to this reference

Fulltext file(s):

	File	Commentary	Version	Size	Access
Open access	2007_eric_cbrn_Experiments.pdf		Author postprint	221.65 kB	View/Open

All documents in ORBi^lu are protected by a user license.