PhD Studentship: Engineering Reliable and Efficient Networked Machine Learning via the Free Energy Principle

Overview

Description

Inspired by neuroscience, informed by information-theoretic principles, and motivated by modern wireless systems architectures integrating artificial intelligence (AI) and communications, this project, supported by the EPSRC, sets out to develop a paradigm-shifting framework for networked machine learning (ML) that is centred on the following ideas.

Free energy minimisation: According to the free energy principle, agents optimise internal models so as to minimise their information-theoretic surprise vis-a-vis the available data and prior information. This principle offers a basis to reason about epistemic uncertainty ("know when you don't know") in AI agents that is grounded in information-theoretic analyses of out-of-sample generalisation - away from the current narrow focus on point-wise accuracy, towards uncertainty quantification and calibration. 

Networked meta-learning: In meta-learning, agents do not share an ML model in full as in conventional, centralised, solutions. 

Native integration of wireless communication and learning: Conventional wireless systems are based on the principle of separation between computing and communications.

Overall, this project sets out to study a novel, theoretically principled, paradigm for ML that moves away from the current centralised, accuracy-focused, state of the art in ML to embrace decentralization via wireless connectivity, uncertainty quantification, personalisation, modularity, privacy preservation, and the right to erasure.

Applicable programmes

Benefits

Funding is available for 3.5 years (covering Tuition fees, Stipend plus London Allowance, Bench Fees/Research Training & Support Grant). It covers tuition fees for UK or International students and a tax-free stipend of approximately £19,668 p.a. with possible inflationary increases after the first year.