Relational Networks for goal-directed sensory-motor task
We will build a (relatively) simple spiking neuronal network implementing a goal-directed state-to-action mapping (SAG) unit. As a core architecture we will use a three-way relation network proposed by [1]. However, we would like to translate the rate-coding scheme into spike time coding scheme to exploit spatio-temporal sparsity of the network. The aim of this workshop is to implement and test a "hard-wired" version of this relational network on a neuromorphic processor (e.g. the DYNAP-SE chip), encoding behavior (i.e. mapping the Stimulus position to the Pointer position) of an "agent" for various goals: (a) following the stimulus, (b) avoiding the stimulus, (c) keeping a fixed distance to the stimulus.
References:
[1] P. U. Diehl and M. Cook, “Learning and inferring relations in cortical networks”, arXiv preprint, arXiv:1608.08267, 2016.
Timetable
| Day | Time | Location |
|---|---|---|
| Tue, 24.04.2018 | 22:00 - 23:00 | Lecture Room |
| Wed, 25.04.2018 | 21:00 - 22:00 | Lab / Disco |
| Thu, 26.04.2018 | 22:00 - 23:00 | Lecture Room |
| Tue, 01.05.2018 | 10:00 - 12:00 | Lab |