eSSENCE@LU 4:1 - Method development for analysis and modelling of large scale electrophysiological recordings using deep artificial neural networks
Aim 1 : To develop plausible systems-level network models that can reproduce observed neurophysiological data and generate testable hypotheses about policy/ value functions Method: To extend and connect existing computational models of cortex and basal ganglia and to enhance them with data on network functional connectivity estimated from electrophysiological measurements.
Aim 2: To evaluate action-based learning in autonomous humanoid robots Method: Humanoid robots learn to control an artificial hand in a skilled reaching task by action-based learning and sensory feedback combining systems for intelligent perception with autonomous robotic systems and direct comparisons to brain processes are made.
|Short title||eSSENCE@LU 4:1|
|Effective start/end date||2017/07/01 → 2020/06/30|
- Christian Balkenius - eSSENCE: The e-Science Collaboration (PI)
- Per Petersson - eSSENCE: The e-Science Collaboration (Researcher)
- Karl Åström - Mathematics (Faculty of Engineering) (Researcher)
- Trond Arild Tjøstheim - Cognitive Science (Researcher)
- Birger Johansson - LUCS Robotics Group (Researcher)
- Joel Sjöbom - MultiPark: Multidisciplinary research focused on Parkinson´s disease (Researcher)
Kalle Åström, Jacek Malec, Stefan Larsson, Mattias Ohlsson, Christian Balkenius, Anamaria Dutceac Segesten, Jutta Haider, Robert Willim, Jonas Ledendal, Jonas Wisbrant, Elin Anna Topp, Jörn Janneck, Marcus Klang, Einar Heiberg, Katja de Vries & Ingar Brinck
2018/01/01 → …