You will develop novel active AI algorithms that are inspired by the rapid and robust learning of insects within the £1.2m EPSRC International Centre to Centre Collaboration project: “ActiveAI: active learning and selective attention for rapid, robust and efficient AI.” and will work in collaboration with the University of Sheffield and world-leading neuroscientists in Australia. Your primary role will be to 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 learning 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. The cycle of modelling and experiments will be achieved through field work in both Sussex and Australia.

A fully-funded PhD is available with Dr Silvia Maggi and Professor Mark Humphries (University of Nottingham) and Dr Hazem Toutonji (University of Sheffield). The project involves understanding how subjects respond to dynamic environments and requires approaches that can track subject's choice strategies at the resolution of single trials. The team recently developed a Bayesian inference algorithm that enables trial-resolution tracking of learning and exploration during learning. This project will build on this work to solve crucial problems of determining which of a set of behavioural strategies a subject is using and how to incorporate evidence uncertainty into its detection of the learning of strategies and transitions between them. Using the extended algorithm on datasets of rodents and humans performing decision tasks will let us test a range of hypotheses for how correct decisions are learnt and what innate strategies are used.

A fully-funded PhD is available with Dr Silvia Maggi and Professor Mark Humphries (University of Nottingham) and Dr Hazem Toutonji (University of Sheffield). The project involves understanding how subjects respond to dynamic environments and requires approaches that can track subject's choice strategies at the resolution of single trials. The project will build on a recently developed Bayesian inference algorithm that enables trial-resolution tracking of learning and exploration during learning. The project aims to solve crucial problems of determining which of a set of behavioural strategies a subject is using and how to incorporate evidence uncertainty into its detection of the learning of strategies and transitions between them. Using the extended algorithm on datasets of rodents and humans performing decision tasks will let us test a range of hypotheses for how correct decisions are learnt and what innate strategies are used.

A fully-funded PhD is immediately available with Dr Silvia Maggi and Professor Mark Humphries (University of Nottingham) and Dr Hazem Toutonji (University of Sheffield). The project will build on recently published work involving a Bayesian inference algorithm that enables trial-resolution tracking of learning and exploration during decision-making. The PhD project aims to solve crucial problems of determining which of a set of behavioural strategies a subject is using and how to incorporate evidence uncertainty into its detection of the learning of strategies and transitions between them. Using the extended algorithm on datasets of rodents and humans performing decision tasks will allow testing a range of hypotheses for how correct decisions are learnt and what innate strategies are used.