Learning Descriptors for Novelty-Search Based Instance Generation via Meta-evolution
Conference Proceeding
Marrero, A., Segredo, E., León, C., & Hart, E. (in press)
Learning Descriptors for Novelty-Search Based Instance Generation via Meta-evolution. In Genetic and Evolutionary Computation Conference (GECCO ’24), July 14–18, 2024, Melbourne, VIC, Australia. https://doi.org/10.1145/3638529.3654028
The ability to generate example instances from a domain is important in order to benchmark algorithms and to generate data that covers an instance-space in order to train mach...
A Hierarchical Approach to Evolving Behaviour-Trees for Swarm Control
Conference Proceeding
Montague, K., Hart, E., & Paechter, B. (2024)
A Hierarchical Approach to Evolving Behaviour-Trees for Swarm Control. In S. Smith, J. Correia, & C. Cintrano (Eds.), Applications of Evolutionary Computation: 27th European Conference, EvoApplications 2024, Held as Part of EvoStar 2024, Aberystwyth, UK, April 3–5, 2024, Proceedings, Part I (178-193). https://doi.org/10.1007/978-3-031-56852-7_12
Behaviour trees (BTs) are commonly used as controllers in robotic swarms due their modular composition and to the fact that they can be easily interpreted by humans. From an a...
On the Utility of Probing Trajectories for Algorithm-Selection
Conference Proceeding
Renau, Q., & Hart, E. (2024)
On the Utility of Probing Trajectories for Algorithm-Selection. In Applications of Evolutionary Computation. EvoApplications 2024 (98-114). https://doi.org/10.1007/978-3-031-56852-7_7
Machine-learning approaches to algorithm-selection typically take data describing an instance as input. Input data can take the form of features derived from the instance desc...
How Much do Robots Understand Rudeness? Challenges in Human-Robot Interaction
Conference Proceeding
Orme, M., Yu, Y., & Tan, Z. (in press)
How Much do Robots Understand Rudeness? Challenges in Human-Robot Interaction.
This paper concerns the pressing need to understand and manage inappropriate language within the evolving human-robot interaction (HRI) landscape. As intelligent systems and r...
Can Federated Models Be Rectified Through Learning Negative Gradients?
Conference Proceeding
Tahir, A., Tan, Z., & Babaagba, K. O. (2024)
Can Federated Models Be Rectified Through Learning Negative Gradients?. In Big Data Technologies and Applications (18-32). https://doi.org/10.1007/978-3-031-52265-9_2
Federated Learning (FL) is a method to train machine learning (ML) models in a decentralised manner, while preserving the privacy of data from multiple clients. However, FL is...
Evolving Behavior Allocations in Robot Swarms
Conference Proceeding
Hallauer, S., Nitschke, G., & Hart, E. (2024)
Evolving Behavior Allocations in Robot Swarms. In 2023 IEEE Symposium Series on Computational Intelligence (SSCI) (1526-1531). https://doi.org/10.1109/SSCI52147.2023.10371934
Behavioral diversity is known to benefit problem-solving in biological social systems such as insect colonies and human societies, as well as in artificial distributed systems...
Too Constrained for Genetic Algorithms. Too Hard for Evolutionary Computing. The Traveling Tournament Problem.
Conference Proceeding
Verduin, K., Thomson, S. L., & van den Berg, D. (2023)
Too Constrained for Genetic Algorithms. Too Hard for Evolutionary Computing. The Traveling Tournament Problem. In Proceedings of the 15th International Joint Conference on Computational Intelligence (246-257). https://doi.org/10.5220/0012192100003595
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...
Can HP-protein folding be solved with genetic algorithms? Maybe not
Conference Proceeding
Jansen, R., Horn, R., van Eck, O., Version, K., Thomson, S. L., & van den Berg, D. (2023)
Can HP-protein folding be solved with genetic algorithms? Maybe not. In Proceedings of the 15th International Joint Conference on Computational Intelligence (131-140). https://doi.org/10.5220/0012248500003595
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...
The Opaque Nature of Intelligence and the Pursuit of Explainable AI
Conference Proceeding
Thomson, S. L., van Stein, N., van den Berg, D., & van Leeuwen, C. (2023)
The Opaque Nature of Intelligence and the Pursuit of Explainable AI. In Proceedings of the 15th International Joint Conference on Computational Intelligence (555-564). https://doi.org/10.5220/0012249500003595
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 ...
Augmenting Novelty Search with a Surrogate Model to Engineer Meta-Diversity in Ensembles of Classifiers
Conference Proceeding
Cardoso, R. P., Hart, E., Burth Kurka, D., & Pitt, J. (2022)
Augmenting Novelty Search with a Surrogate Model to Engineer Meta-Diversity in Ensembles of Classifiers. In Applications of Evolutionary Computation: EvoApplications 2022 (418-434). https://doi.org/10.1007/978-3-031-02462-7_27
Using Neuroevolution combined with Novelty Search to promote behavioural diversity is capable of constructing high-performing ensembles for classification. However, using grad...