Don't miss our weekly PhD newsletter | Sign up now Don't miss our weekly PhD newsletter | Sign up now

  Human-in-the-loop Generative Models for Experimental Design


   Department of Computer Science

This project is no longer listed on FindAPhD.com and may not be available.

Click here to search FindAPhD.com for PhD studentship opportunities
  Prof Samuel Kaski  No more applications being accepted  Competition Funded PhD Project (UK Students Only)

About the Project

The UKRI AI Centre for Doctoral Training (CDT) in Decision Making for Complex Systems is a joint CDT between The University of Manchester and the University of Cambridge. The CDT provides funding for four years of advanced studies towards a PhD. The first year consists of a taught program at Manchester that will cover the fundamentals of Machine Learning. This year is followed by three years of research at either at Manchester or Cambridge. Please note the research element of the PhD will take place at the host institution of the supervisor listed for each project.

Background & Challenges: Experimental Design, which is the driving force of all empirical science and much of product development, often involves brute-force trial and error to reach a desired outcome which may not be optimal. While we have seen successful applications of AI driven experimental design, they are still limited and tailored to a particular dataset and research question. Challenges still remain: (1) The stages in a typical experimental design are still rather expensive and while AI-assistance is available for some individual operations, automation is not yet widely affordable. As a consequence, the available datasets consisting of many designs for one specific experiment can be quite limited -- Small data [1]; (2) Each design can have a seemingly vast amount of multi-modal, multi-task and multi-embodiment data generated from a typical high-throughput experiment, but the large number of variables makes the problem only harder when sample size remains severely small -- Heterogeneous inputs; and (3) Generalizing from the small-scale experiments in design cycles to forecast the behavior of next iteration of design, and further to laboratories at a larger scale is fundamentally difficult as machine learning is notoriously bad in generalizing outside the training distribution without first-principles – Domain knowledge [2].

Objectives: This project aims to use human-in-the-loop generative models for experimental design. Specifically, the project will use generative models to capture the underlying distribution of well designed experiments and then transfer to unseen experiments. The transferring will leverage

Bayesian optimal experimental design methods to bring expert domain knowledge to bear in the sequential decision task of navigating the design space even with small heterogeneous data [3, 4]. With Bayesian experimental design principles we can choose the next experiment to run, combining candidates from generative models of experiments, and data collected so far from measurements and the user. This experimental design approach will be integrated with transformers to handle heterogeneous data that merges experimentally generated patterns and model-generated databases.

We will test the principles in running the Design-Build-Test-Learn (DBTL) loops in Synthetic Biology, where we have outstandingly interesting case studies available through the collaboration of the supervisors, and ultimately can generalize also to other fields with additional collaborations.

Entry requirements

Applicants should have, or expect to achieve, at least a 2.1 honours degree or a master’s (or international equivalent) in a relevant science or engineering related discipline.

How to Apply

As the CDT has only recently been awarded we strongly encourage you to contact the supervisor of the project you are interested in with your CV and supporting documents. You will have a chance to meet with prospective supervisors prior to submitting an application - further details will be provided.

Equality, diversity and inclusion is fundamental to the success of The University of Manchester, and is at the heart of all of our activities. We know that diversity strengthens our research community, leading to enhanced research creativity, productivity and quality, and societal and economic impact.

We actively encourage applicants from diverse career paths and backgrounds and from all sections of the community, regardless of age, disability, ethnicity, gender, gender expression, sexual orientation and transgender status.

We also support applications from those returning from a career break or other roles. We consider offering flexible study arrangements (including part-time: 50%, 60% or 80%, depending on the project/funder).

AI_CDT_DecisionMaking

Computer Science (8) Engineering (12) Mathematics (25)

Funding Notes

Funding includes tuition fees and stipend at the UKRI minimum rate, currently £18,622/annum (see https://www.ukri.org/apply-for-funding/studentships-and-doctoral-training/changes-to-the-minimum-stipend-from-1-october-2023/ for further information). Studentship funding is for 4 years. This scheme is open to both the UK and international applicants. We are only able to offer a limited number of studentships to applicants outside the UK.

How good is research at The University of Manchester in Computer Science and Informatics?


Research output data provided by the Research Excellence Framework (REF)

Click here to see the results for all UK universities
Search Suggestions
Search suggestions

Based on your current searches we recommend the following search filters.