[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).
Disciplines :
Sciences informatiques
Auteur, co-auteur :
ANTONELO, Eric Aislan ; University of Luxembourg > Interdisciplinary Centre for Security, Reliability and Trust (SNT)
Schrauwen, Benjamin
Stroobandt, Dirk
Co-auteurs externes :
yes
Langue du document :
Anglais
Titre :
Experiments with Reservoir Computing on the road sign problem
Date de publication/diffusion :
2007
Nom de la manifestation :
VIII Brazilian Congress on Neural Networks (CBRN)
Date de la manifestation :
Oct 2007
Manifestation à portée :
International
Titre de l'ouvrage principal :
Proceedings of the VIII Brazilian Congress on Neural Networks (CBRN)
