|
Learning and Selecting Behaviours with Dynamic Neural Fields| old_uid | 15972 |
|---|
| title | Learning and Selecting Behaviours with Dynamic Neural Fields |
|---|
| start_date | 2015/07/21 |
|---|
| schedule | 10h |
|---|
| online | no |
|---|
| location_info | 5e étage, salle 570 |
|---|
| summary | Dynamic Neural Fields are neurally-inspired dynamical systems, which allow to model cognitive functions, such as memory formation, decision making, stabilisation of control parameters, feature binding, and executive control. In this talk, I will describe how DNFs were extended recently into a structural representation of intentional behaviours, which features a representation of the intention and the condition of satisfaction of each action. I will demonstrate how this new structure allows to learn behaviors autonomously and to organise their activation and deactivation in an appropriate sequence, leading to a behavioural goal. |
|---|
| responsibles | Marinica |
|---|
| |
|