[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 :
Computer science
Author, co-author :
ANTONELO, Eric Aislan ; University of Luxembourg > Interdisciplinary Centre for Security, Reliability and Trust (SNT)
Schrauwen, Benjamin
Stroobandt, Dirk
External co-authors :
yes
Language :
English
Title :
Experiments with Reservoir Computing on the road sign problem
Publication date :
2007
Event name :
VIII Brazilian Congress on Neural Networks (CBRN)
Event date :
Oct 2007
Audience :
International
Main work title :
Proceedings of the VIII Brazilian Congress on Neural Networks (CBRN)
