FindAPhD Weekly PhD Newsletter | JOIN NOW FindAPhD Weekly PhD Newsletter | JOIN NOW

Principled Application of Evolutionary Algorithms


   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
  Dr Christine Zarges  No more applications being accepted  Funded PhD Project (Students Worldwide)

About the Project

The UKRI CDT in Artificial Intelligence, Machine Learning and Advanced Computing (AIMLAC) aims at forming the next generation of AI innovators across a broad range of STEMM disciplines. The CDT provides advanced multi-disciplinary training in an inclusive, caring and open environment that nurture each individual student to achieve their full potential. Applications are encouraged from candidates from a diverse background that can positively contribute to the future of our society. 

The UK Research and Innovation (UKRI) fully-funded scholarships cover the full cost of tuition fees, a UKRI standard stipend of £15,921 per annum and additional funding for training, research and conference expenses. The scholarships are open to UK and international candidates.

Closing date for applications is 12 February 2022. For further information on how to apply please click here and select the "UKRI CDT Scholarship in AIMLAC" tab.

Project Overview

Evolutionary algorithms are general and robust problem solvers that are inspired by the concept of natural evolution. Over the last decades, they have successfully been applied to a wide range of optimisation and learning tasks in real-world applications. Recently, some researchers [1,2] argue that evolutionary computation now has the potential to become more powerful than deep learning: While deep learning focuses on models of existing knowledge, evolutionary computation has the additional ability to discover new knowledge by creating novel and sometimes even surprising solutions through massive exploration of the search space.

 While evolutionary computation methods are often easy to implement and apply, to achieve good performance, it is usually necessary to adjust them to the problem at hand. The main goal of this project is to exploit recent theoretical advances that shed light on the fundamental working principles of evolutionary algorithms [3] in real-world applications. It will build upon recent momentum and progress in both, theory and applications of evolutionary algorithms and related randomised search heuristics and further contribute to bridging the gap between these two branches of evolutionary computation research [4]. Starting point for the investigations will be modern benchmarking frameworks, e.g., [5,6], and competitions that tackle important societal and industrial challenges, see [7,8] for examples. Possible application areas can be discussed with the supervisors. They include but are not limited to routing, scheduling, and planning problems, bioinformatics, as well as benchmarking and combinatorial optimisation in general.


References

[1] Neural Networks Research Group at the University of Texas at Austin. Evolution is the new deep learning. http://nn.cs.utexas.edu/pages/evolutionary-ai/newdeeplearning/
[2] Risto Miikkulainen. https://venturebeat.com/2018/05/17/evolutionary-computation-will-drive-the-future-of-creative-ai/
[3] Benjamin Doerr, Frank Neumann (eds). Theory of Evolutionary Computation - Recent Developments in Discrete Optimization. Springer, 2020. http://doi.org/10.1007/978-3-030-29414-4
[4] COST ACTION CA15140: http://imappnio.dcs.aber.ac.uk
[5] IOH Profiler. https://iohprofiler.github.io
[6] Nevergrad. https://facebookresearch.github.io/nevergrad/
[7] ACM GECCO 2021 Competitions. https://gecco-2021.sigevo.org/Competitions
[8] IEEE CEC 2021 Competitions. https://cec2021.mini.pw.edu.pl/en/program/competitions

Search Suggestions
Search suggestions

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

PhD saved successfully
View saved PhDs