[Comp-neuro] 3 year Research Fellow in Bio-Inspired Artificial Intelligence and Robotics at the University of Sussex
T.Nowotny at sussex.ac.uk
Wed Aug 28 20:13:38 CEST 2019
Research Fellow in Bio-Inspired Artificial Intelligence and Robotics at the University of Sussex
Are you a talented and ambitious computer scientist, computational neuroscientist or machine learner? Are you looking for an opportunity to use cutting edge technology to gain new understanding of how small-brained insects learn so rapidly and robustly, and in turn develop novel active AI algorithms that are inspired by these insights? We have an opportunity for a Research Fellow to join the Brains on Board<http://brainsonboard.co.uk/> team at the Department of Informatics at the University of Sussex to join a collaboration with the University of Sheffield and world-leading neuroscientists in Australia through the EPSRC-funded ActiveAI project: active learning and selective attention for rapid, robust and efficient AI.
You will develop a new class of ActiveAI controllers for problems in which insects excel but deep learning methods struggle. These problems have one or more of the following characteristics: (i) learning must occur rapidly, (ii) learning samples are few or costly, (iii) computational resources are limited, and (iv) the problem changes over time. Insects deal with such complex tasks robustly despite limited computational power because learning is an active process emerging from the interaction of evolved brains, bodies and behaviours. Through a virtuous cycle of modelling and experiments, you will develop insect-inspired models, in which behavioural strategies and specialised sensors actively structure sensory input while selective attention drives learning to the most salient information. This will be achieved through extended visits to Australia, in which you will interact with biologists and shape novel insect experiments that in turn will inspire computational and robotic models and novel algorithms. In this way, we will both advance neuroscience and enable ActiveAI solutions which will be efficient in final network configuration, robust to real-world conditions and learn rapidly.
This project includes significant scope for you to creatively shape and drive the project to your interests and to organise the timing and length of your visits to Australia. You will work under the supervision of Professors Andrew Philippides, Thomas Nowotny and Paul Graham at Sussex as well as the wider Brains on Board team and, together with a partner research fellow at Sheffield University, you will lead a new collaboration with world-leading Australian research partners through extended secondments.
Closing date: midnight UK BST, 23 September 2019.
For full details see: https://www.sussex.ac.uk/about/jobs/rf-artifical-intellience-robotics-2091
Prof Thomas Nowotny
Director of Research and Knowledge Exchange
School of Engineering and Informatics
University of Sussex
Falmer, Brighton BN1 9QJ, UK
-------------- next part --------------
An HTML attachment was scrubbed...
More information about the Comp-neuro