Experiments with Reservoir Computing on the road sign problem
| Title | Experiments with Reservoir Computing on the road sign problem |
| Publication Type | Conference Proceedings |
| Year of Conference | 2007 |
| Authors | Antonelo EA, Schrauwen B, Stroobandt D |
| Conference Name | Proceedings of the VIII Brazilian Congress on Neural Networks (CBRN) |
| Publisher | SBRN |
| Abstract | 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). |
| URL | http://abricom.org.br/eventos/cbrn_2007/50100047-2/ |
| DOI | 10.21528/CBRN2007-047 |
Draft File:
