I will be hiring a number of post-doctoral fellows and taking on some PhD students for the ERC project “Generalization in Mind and Machine”. If you have skill in neural network modelling and find the project interesting, please send me an email. For potential PhD students, some background in modelling is a plus, but not strictly necessary. Computer scientists with training in deep networks also encouraged to apply.
Job number | ACAD103102
ERC Senior Research Associate
£36,613 – £41,212 per annum
Closing date | Thursday 15 March 2018 (23:59 GMT)
How to apply | Please apply at the University of Bristol Website
This five year ERC-funded project entitled “Generalisation in Mind and Machine” explores how well neural networks support human-like generalisation across a range of tasks. Over the course of the grant there will be four post-doctoral fellows involved in modelling, one research assistant involved in empirical work, and two PhD students. This is one of three modelling posts that runs for three years. I am looking to hire someone with a PhD in computer science or cognitive psychology (or related field) who has experience working with neural networks.
In contrast with the large community of researchers focused on improving the performance of deep networks for applied reasons, the goal of this project is to explore what neural networks tell us about how the brain works. More specifically, the team will be working on questions of generalisation in the domains of object identification, word identification, short-term memory, and games, amongst other areas. This research is related to previous and ongoing research in my lab that explores why and when artificial neural networks learn localist “grandmother cell” representations with the goal to better understand why some neurons respond to high-level information in a highly selective manner. For more information please visit my ‘Research’ section.
Applications should include curriculum vitae, list of publications, and a brief description of research interests. This post is available from 1st May 2018 (but somewhat flexible about start date) and currently has funding secured until May 2021.
For informal enquiries please contact me at J.Bowers@bristol.ac.uk
Relevant papers include
Bowers, J. S. (2017). Parallel Distributed Processing Theory in the Age of Deep Networks. Trends in Cognitive Sciences, 12, 950-961.
Bowers, J. S., Vankov, I. I., Damian, M. F., & Davis, C. J. (2016). Why do some neurons in cortex respond to information in a selective manner? Insights from artificial neural networks. Cognition, 148, 47-63.
Bowers, J.S., & Davis, C.J. (in preparation). Implementing symbolic processes in neural networks through myelin plasticity.