Do you want to be responsible for the development and validation of maths and models under supervision of expert staff in machine learning? Then we invite you to apply for a PhD position on 'Bio-inspired learning algorithms for efficient and robust neural network models with a focus on neuromorphic computing and control of complex environments'.
This project is embedded within the
European Laboratory for Learning and Intelligent Systems (ELLIS) Unit in Radboud AI. The aim is to develop highly effective algorithms for training artificial neural network models which make use of (biologically plausible) information local to the individual nodes of the network. This locality will allow efficient implementation and testing of these algorithms on neuromorphic computing systems. The efficacy of the algorithms will be tested in simulations. This will be done in the context of relevant reinforcement learning tasks using a control system theoretic approach to interaction with modelled environments. This work entails a theoretical (mathematical) development of state-of-the-art biologically plausible learning rules and reinforcement learning strategies alongside implementation/testing of these algorithms in the form of neuromorphic computing algorithms and agent-based artificial neural network modelling.
We offer you a full-time (100%) position for 4 years. This project is supervised by Prof. van Gerven, Dr Nasir Ahmad and Dr. Bodo Rueckauer. You will be employed at the Artificial Intelligence department of the Donders Institute for Brain, Cognition and Behaviour, where you will have the opportunity to collaborate and interact with renowned international experts in machine learning, computational neuroscience and neuromorphic computing. You will also benefit from the extensive training programme of the Donders Graduate School. Additionally, you will have the opportunity to supervise MSc and BSc students in their thesis projects. 10% of your appointment will be devoted to support tasks in the ELLIS unit, such as helping to organise ELLIS activities or (co)supervision of ELLIS-related projects.