Sarah L. Thomson
sarah l thomson

Dr Sarah L. Thomson

Lecturer

Biography

Dr Sarah L. Thomson is a lecturer in data science at 麻豆社区, having started there in August 2023. She was previously at the University of Stirling: she was awarded her PhD there in March 2021, and worked as a research fellow from September 2020 until May 2022; after that. she took up a lectureship in June 2022, before moving to Edinburgh Napier in August 2023.

Dr Thomson's expertise is predominantly in evolutionary computation, optimisation, and machine learning. She has worked on problems from healthcare, aviation, vehicle management, and agriculture. Additionally, she has a passion for fundamental research and is particularly interested in fitness landscapes and explainable artificial intelligence (XAI).

Research Areas

Date


28 results

The fractal geometry of fitness landscapes at the local optima level

Journal Article
Thomson, S. L., Ochoa, G., & Verel, S. (2022)
The fractal geometry of fitness landscapes at the local optima level. Natural Computing, 21(2), 317-333. https://doi.org/10.1007/s11047-020-09834-y
A local optima network (LON) encodes local optima connectivity in the fitness landscape of a combinatorial optimisation problem. Recently, LONs have been studied for their fra...

Inferring Future Landscapes: Sampling the Local Optima Level

Journal Article
Thomson, S. L., Ochoa, G., Verel, S., & Veerapen, N. (2020)
Inferring Future Landscapes: Sampling the Local Optima Level. Evolutionary Computation, 28(4), 621-641. https://doi.org/10.1162/evco_a_00271
Connection patterns among Local Optima Networks (LONs) can inform heuristic design for optimisation. LON research has predominantly required complete enumeration of a fitness ...

The Local Optima Level in Chemotherapy Schedule Optimisation

Presentation / Conference Contribution
Thomson, S. L., & Ochoa, G. (2020, April)
The Local Optima Level in Chemotherapy Schedule Optimisation. Presented at EvoCOP 2020: Evolutionary Computation in Combinatorial Optimization, Seville, Spain
In this paper a multi-drug Chemotherapy Schedule Optimisation Problem (CSOP) is subject to Local Optima Network (LON) analysis. LONs capture global patterns in fitness landsca...

Clarifying the Difference in Local Optima Network Sampling Algorithms

Presentation / Conference Contribution
Thomson, S. L., Ochoa, G., & Verel, S. (2019, April)
Clarifying the Difference in Local Optima Network Sampling Algorithms. Presented at 19th European Conference, EvoCOP 2019, Leipzig, Germany
We conduct the first ever statistical comparison between two Local Optima Network (LON) sampling algorithms. These methodologies attempt to capture the connectivity in the loc...

Multifractality and dimensional determinism in local optima networks

Presentation / Conference Contribution
Thomson, S. L., Verel, S., Ochoa, G., Veerapen, N., & Cairns, D. (2018, July)
Multifractality and dimensional determinism in local optima networks. Presented at GECCO '18: Genetic and Evolutionary Computation Conference, Kyoto, Japan
We conduct a study of local optima networks (LONs) in a search space using fractal dimensions. The fractal dimension (FD) of these networks is a complexity index which assigns...

On the Fractal Nature of Local Optima Networks

Presentation / Conference Contribution
Thomson, S. L., Verel, S., Ochoa, G., Veerapen, N., & McMenemy, P. (2018, April)
On the Fractal Nature of Local Optima Networks. Presented at 18th European Conference: EvoCOP 2018, Parma, Italy
A Local Optima Network represents fitness landscape connectivity within the space of local optima as a mathematical graph. In certain other complex networks or graphs there ha...

The effect of landscape funnels in QAPLIB instances

Presentation / Conference Contribution
Thomson, S. L., Ochoa, G., Daolio, F., & Veerapen, N. (2017, July)
The effect of landscape funnels in QAPLIB instances. Presented at GECCO '17: Genetic and Evolutionary Computation Conference, Berlin, Germany
The effectiveness of common metaheuristics on combinatorial optimisation problems can be limited by certain characteristics of the fitness landscape. We use the local optima n...

Comparing communities of optima with funnels in combinatorial fitness landscapes

Presentation / Conference Contribution
Thomson, S. L., Daolio, F., & Ochoa, G. (2017, July)
Comparing communities of optima with funnels in combinatorial fitness landscapes. Presented at GECCO '17: Genetic and Evolutionary Computation Conference, Berlin, Germany
The existence of sub-optimal funnels in combinatorial fitness landscapes has been linked to search difficulty. The exact nature of these structures --- and how commonly they a...

Current Post Grad projects