Outputs (120)

Channel Configuration for Neural Architecture: Insights from the Search Space (2023)
Presentation / Conference Contribution
Thomson, S. L., Ochoa, G., Veerapen, N., & Michalak, K. (2023, July). Channel Configuration for Neural Architecture: Insights from the Search Space. Presented at GECCO '23, Lisbon, Portugal

We consider search spaces associated with neural network channel configuration. Architectures and their accuracy are visualised using low-dimensional Euclidean embedding (LDEE). Optimisation dynamics are captured using local optima networks (LONs). L... Read More about Channel Configuration for Neural Architecture: Insights from the Search Space.

From Fitness Landscapes to Explainable AI and Back (2023)
Presentation / Conference Contribution
Thomson, S. L., Adair, J., Brownlee, A. E. I., & van den Berg, D. (2023, July). From Fitness Landscapes to Explainable AI and Back. Presented at GECCO '23, Lisbon, Portugal

We consider and discuss the ways in which search landscapes might contribute to the future of explainable artificial intelligence (XAI), and vice versa. Landscapes are typically used to gain insight into algorithm search dynamics on optimisation prob... Read More about From Fitness Landscapes to Explainable AI and Back.

Randomness in Local Optima Network Sampling (2023)
Presentation / Conference Contribution
Thomson, S. L., Veerapen, N., Ochoa, G., & van den Berg, D. (2023, July). Randomness in Local Optima Network Sampling. Presented at GECCO '23, Lisbon, Portugal

We consider statistical randomness in the construction of local optima networks (LONs) and conduct a preliminary and exploratory study into this. LONs capture a fitness landscape into network format: the nodes are local optima, and edges are heuristi... Read More about Randomness in Local Optima Network Sampling.

Universally Hard Hamiltonian Cycle Problem Instances (2022)
Presentation / Conference Contribution
Sleegers, J., Thomson, S. L., & van den Berg, D. (2022, November). Universally Hard Hamiltonian Cycle Problem Instances. Presented at ECTA 2022 : 14th International Conference on Evolutionary Computation Theory and Applications, Valletta, Malta

In 2021, evolutionary algorithms found the hardest-known yes and no instances for the Hamiltonian cycle problem. These instances, which show regularity patterns, require a very high number of recursions for the best exact backtracking algorithm (Vand... Read More about Universally Hard Hamiltonian Cycle Problem Instances.

Frequency Fitness Assignment on JSSP: A Critical Review (2023)
Presentation / Conference Contribution
de Bruin, E., Thomson, S. L., & Berg, D. V. D. (2023, April). Frequency Fitness Assignment on JSSP: A Critical Review. Presented at EvoApplications 2023: Applications of Evolutionary Computation, Brno, Czech Republic

Metaheuristic navigation towards rare objective values instead of good objective values: is it a good idea? We will discuss the closed and open ends after presenting a successful replication study of Weise et al.’s ‘frequency fitness assignment’ for... Read More about Frequency Fitness Assignment on JSSP: A Critical Review.

Fractal Dimension and Perturbation Strength: A Local Optima Networks View (2022)
Presentation / Conference Contribution
Thomson, S. L., Ochoa, G., & Verel, S. (2022, September). Fractal Dimension and Perturbation Strength: A Local Optima Networks View

We study the effect of varying perturbation strength on the fractal dimensions of Quadratic Assignment Problem (QAP) fitness landscapes induced by iterated local search (ILS). Fitness landscapes are represented as Local Optima Networks (LONs), which... Read More about Fractal Dimension and Perturbation Strength: A Local Optima Networks View.

On funnel depths and acceptance criteria in stochastic local search (2022)
Presentation / Conference Contribution
Thomson, S. L., & Ochoa, G. (2022). On funnel depths and acceptance criteria in stochastic local search. In GECCO '22: Proceedings of the Genetic and Evolutionary Computation Conference (287-295). https://doi.org/10.1145/3512290.3528831

We propose looking at the phenomenon of fitness landscape funnels in terms of their depth. In particular, we examine how the depth of funnels in Local Optima Networks (LONs) of benchmark Quadratic Assignment Problem instances relate to metaheuristic... Read More about On funnel depths and acceptance criteria in stochastic local search.

The fractal geometry of fitness landscapes at the local optima level (2020)
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 fractal dimension. Fractal dimension is a complexity index where a non-integer... Read More about The fractal geometry of fitness landscapes at the local optima level.

The Local Optima Level in Chemotherapy Schedule Optimisation (2020)
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 landscapes. CSOPs have not previously been subject to fitness landscape analysis.... Read More about The Local Optima Level in Chemotherapy Schedule Optimisation.

Inferring Future Landscapes: Sampling the Local Optima Level (2020)
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 landscape, thereby restricting analysis to problems diminutive in size comp... Read More about Inferring Future Landscapes: Sampling the Local Optima Level.

Clarifying the Difference in Local Optima Network Sampling Algorithms (2019)
Presentation / Conference Contribution
Thomson, S. L., Ochoa, G., & Verel, S. (2019). Clarifying the Difference in Local Optima Network Sampling Algorithms. In Evolutionary Computation in Combinatorial Optimization. EvoCOP 2019 (163-178). https://doi.org/10.1007/978-3-030-16711-0_11

We conduct the first ever statistical comparison between two Local Optima Network (LON) sampling algorithms. These methodologies attempt to capture the connectivity in the local optima space of a fitness landscape. One sampling algorithm is based on... Read More about Clarifying the Difference in Local Optima Network Sampling Algorithms.

The Opaque Nature of Intelligence and the Pursuit of Explainable AI (2023)
Presentation / Conference Contribution
Thomson, S. L., van Stein, N., van den Berg, D., & van Leeuwen, C. (2023, November). The Opaque Nature of Intelligence and the Pursuit of Explainable AI. Presented at NCTA 2023: 15th International Conference on Neural Computation Theory and Applications, Rome, Italy

When artificial intelligence is used for making decisions, people are more likely to accept those decisions if they can be made intelligible to the public. This understanding has led to the emerging field of explainable artificial intelligence. We re... Read More about The Opaque Nature of Intelligence and the Pursuit of Explainable AI.

Too Constrained for Genetic Algorithms. Too Hard for Evolutionary Computing. The Traveling Tournament Problem. (2023)
Presentation / Conference Contribution
Verduin, K., Thomson, S. L., & van den Berg, D. (2023, November). Too Constrained for Genetic Algorithms. Too Hard for Evolutionary Computing. The Traveling Tournament Problem. Presented at ECTA 2023 15th International Conference on Evolutionary Computation Theory and Applications, Rome, Italy

Unlike other NP-hard problems, the constraints on the traveling tournament problem are so pressing that it’s hardly possible to randomly generate a valid solution, for example, to use in a genetic algorithm’s initial population. In this study, we ran... Read More about Too Constrained for Genetic Algorithms. Too Hard for Evolutionary Computing. The Traveling Tournament Problem..

Can HP-protein folding be solved with genetic algorithms? Maybe not (2023)
Presentation / Conference Contribution
Jansen, R., Horn, R., van Eck, O., Version, K., Thomson, S. L., & van den Berg, D. (2023, November). Can HP-protein folding be solved with genetic algorithms? Maybe not. Presented at ECTA 2023 15th International Conference on Evolutionary Computation Theory and Applications, Rome, Italy

Genetic algorithms might not be able to solve the HP-protein folding problem because creating random individuals for an initial population is very hard, if not impossible. The reason for this, is that the expected number of constraint violations incr... Read More about Can HP-protein folding be solved with genetic algorithms? Maybe not.

Leveraging contextual representations with BiLSTM-based regressor for lexical complexity prediction (2023)
Journal Article
Aziz, A., Hossain, M. A., Chy, A. N., Ullah, M. Z., & Aono, M. (2023). Leveraging contextual representations with BiLSTM-based regressor for lexical complexity prediction. Natural Language Processing Journal, 5, Article 100039. https://doi.org/10.1016/j.nlp.2023.100039

Lexical complexity prediction (LCP) determines the complexity level of words or phrases in a sentence. LCP has a significant impact on the enhancement of language translations, readability assessment, and text generation. However, the domain-specific... Read More about Leveraging contextual representations with BiLSTM-based regressor for lexical complexity prediction.

Robotics and Autonomous Systems for Environmental Sustainability: Monitoring Terrestrial Biodiversity (2023)
Preprint / Working Paper
Pringle, S., Davies, Z. G., Goddard, M. A., Dallimer, M., Hart, E., Le Goff, L., & Langdale, S. J. (2023). Robotics and Autonomous Systems for Environmental Sustainability: Monitoring Terrestrial Biodiversity

Welcome to the UK-RAS White paper Series on Robotics and Autonomous Systems (RAS). This is one of the core activities of UK-RAS Network, funded by the Engineering and Physical Sciences Research Council (EPSRC). By Bringing together academic centres o... Read More about Robotics and Autonomous Systems for Environmental Sustainability: Monitoring Terrestrial Biodiversity.

enunlg: a Python library for reproducible neural data-to-text experimentation (2023)
Presentation / Conference Contribution
Howcroft, D. M., & Gkatzia, D. (2023). enunlg: a Python library for reproducible neural data-to-text experimentation. In Proceedings of the 16th International Natural Language Generation Conference: System Demonstrations (4-5)

Over the past decade, a variety of neural ar-chitectures for data-to-text generation (NLG) have been proposed. However, each system typically has its own approach to pre-and post-processing and other implementation details. Diversity in implementatio... Read More about enunlg: a Python library for reproducible neural data-to-text experimentation.

The stuff we swim in: Regulation alone will not lead to justifiable trust in AI (2023)
Journal Article
Powers, S. T., Linnyk, O., Guckert, M., Hannig, J., Pitt, J., Urquhart, N., Ekart, A., Gumpfer, N., Han, A., Lewis, P. R., Marsh, S., & Weber, T. (2023). The stuff we swim in: Regulation alone will not lead to justifiable trust in AI. IEEE technology & society magazine, 42(4), 95-106. https://doi.org/10.1109/MTS.2023.3341463

Information technology is used ubiquitously and has become an integral part of everyday life. With the ever increasing pervasiveness and persuasiveness of Artificial Intelligence (AI), the function of socio-technical systems changes and must be consi... Read More about The stuff we swim in: Regulation alone will not lead to justifiable trust in AI.

Expressive Talking Avatars (2024)
Journal Article
Pan, Y., Tan, S., Cheng, S., Lin, Q., Zeng, Z., & Mitchell, K. (2024). Expressive Talking Avatars. IEEE Transactions on Visualization and Computer Graphics, 30(5), 2538-2548. https://doi.org/10.1109/TVCG.2024.3372047

Stylized avatars are common virtual representations used in VR to support interaction and communication between remote collaborators. However, explicit expressions are notoriously difficult to create, mainly because most current methods rely on geome... Read More about Expressive Talking Avatars.

DenMerD: a feature enhanced approach to radar beam blockage correction with edge-cloud computing (2024)
Journal Article
Liu, Q., Sun, J., Zhang, Y., & Liu, X. (2024). DenMerD: a feature enhanced approach to radar beam blockage correction with edge-cloud computing. Journal of cloud computing: advances, systems and applications, 13, Article 32. https://doi.org/10.1186/s13677-024-00607-x

In the field of meteorology, the global radar network is indispensable for detecting weather phenomena and offering early warning services. Nevertheless, radar data frequently exhibit anomalies, including gaps and clutter, arising from atmospheric re... Read More about DenMerD: a feature enhanced approach to radar beam blockage correction with edge-cloud computing.