Job offer Machine Learning Methods for Invariant Representations of High-dimensional Data

Explore a PhD opportunity in the heart of the vibrant Machine Learning community of the University of Bath. Our research project focuses on interpretable machine learning methods designed for high-dimensional data. Specifically, our objective is to develop techniques for recognizing data symmetries and incorporating them as descriptive tools within standard machine learning pipelines. These symmetries are represented as functions that generate data structures that remain invariant when subjected to specific transformations within their domain and are otherwise isomorphic. While it is common practice to derive these representations through deep learning, our project uniquely prioritizes the utilization of explicit mathematical models whenever feasible.

We value flexibility in selecting methodologies, and we highly appreciate novel solutions to the challenges we address. Our project promotes interdisciplinary collaboration, encouraging students to employ creative approaches to problem-solving. Our aim is to cultivate an environment that supports fundamental research in Machine Learning and Deep Learning, offering students the ideal platform for personal development in a research area that holds numerous long-term career prospects.

The domain of application for the developed methods can be agreed upon during the execution of the project. Some indicative applications from ongoing projects include learning representations of astronomical objects, identifying quantum chemical properties of materials, learning representations for medical imaging data (e.g. MRI), and general computer vision tasks. New domains of application are typically treated as a valuable contribution, so long as they lead to high-impact research outcomes.

Computer science » Autonomic computing

Physics » Statistical physics

Physics » Mathematical physics

Physics » Quantum mechanics

Mathematics » Applied mathematics

Computer science » Modelling tools

Mathematics » Computational mathematics

Physics » Computational physics

Researcher Profile
First Stage Researcher (R1), Master Degree or equivalent

Research Field
Mathematics

Education Level
Master Degree or equivalent

Research Field
Computer science

Education Level
Master Degree or equivalent

Skills/Qualifications

Non-UK applicants must meet the programme's English language requirement prior to the closing date of this advert.

Applicants should hold, or expect to receive, a First Class or high Upper Second Class UK Honours degree (or the equivalent) in Mathematics, Physics, Computer Science or a related field. A master's level qualification would also be advantageous.

Specific Requirements

Our expectations include achieving competitive results in machine learning problems and a strong emphasis on the efficient implementation of proposed algorithms. Students are expected to have, or be willing to learn, how to utilize state-of-the-art Machine Learning frameworks and popular libraries for data analysis, including TensorFlow, PyTorch, Jax, Numpy, Scikit-Learn, Pandas, and others.

Languages
ENGLISH, Formal applications should be submitted via the University of Bath's online application form for a PhD in Computer Science prior to the closing date of this advert.

This research project is based at the distinguished University of Bath, which earned the title of University of the Year for 2023 from the Sunday Times. The university is renowned for its unwavering commitment to academic excellence, consistently ranking among the UK's top institutions. Located in the picturesque city of Bath, it offers students a high quality of life. Bath's rich cultural heritage adds a unique dimension to the academic journey, providing an ideal environment for maintaining a strong work-life balance and seeking both academic excellence and a well-rounded, fulfilling experience.