Learning a world model and planning with a self-organizing, dynamic neural system
| dc.creator | Toussaint, Marc | |
| dc.date | 2003-06-11 | |
| dc.date.accessioned | 2026-07-07T05:34:46Z | |
| dc.date.available | 2026-07-07T05:34:46Z | |
| dc.description | We present a connectionist architecture that can learn a model of the relations between perceptions and actions and use this model for behavior planning. State representations are learned with a growing self-organizing layer which is directly coupled to a perception and a motor layer. Knowledge about possible state transitions is encoded in the lateral connectivity. Motor signals modulate this lateral connectivity and a dynamic field on the layer organizes a planning process. All mechanisms are local and adaptation is based on Hebbian ideas. The model is continuous in the action, perception, and time domain. | |
| dc.description | 9 pages, see http://www.marc-toussaint.net/ | |
| dc.identifier | https://arxiv.org/abs/nlin/0306015 | |
| dc.identifier | http://arxiv.org/abs/nlin/0306015 | |
| dc.identifier.uri | http://salesiana.dossiersoluciones.com/handle/123456789/80497 | |
| dc.subject | Adaptation and Self-Organizing Systems | |
| dc.subject | Quantitative Biology | |
| dc.title | Learning a world model and planning with a self-organizing, dynamic neural system | |
| dc.type | text |