My research interests are in the area of evolutionary machine learning. These relate to the analysis of Neuroevolution algorithms through effective visualisation techniques, in order to explain their inherent mechanisms. My research is specifically directed to evolutionary algorithms that evolve both the structure and the weights of Artificial Neural Networks. Precisely, my interests and current work extends to the understanding of efficient utilisation of (indirect) plasticity encoding for said Neural Networks.
Thesis
Neuroevolution Trajectory Networks: illuminating the evolution of artificial neural networks
Sarti S (2024) Neuroevolution Trajectory Networks: illuminating the evolution of artificial neural networks. Doctor of Philosophy. University of Stirling.
Conference Proceeding
Under the Hood of Transfer Learning for Deep Neuroevolution
Sarti S, Laurenço N, Adair J, Machado P & Ochoa G (2023) Under the Hood of Transfer Learning for Deep Neuroevolution. In: Applications of Evolutionary Computation. EvoApplications 2023., 12.04.2023-14.04.2023. Springer Nature Switzerland, pp. 640-655. https://doi.org/10.1007/978-3-031-30229-9_41
Conference Paper (unpublished)
Neuroevolution Trajectory Networks: revealing the past of incrementally neuroevolved CNNs
Sarti S (2023) Neuroevolution Trajectory Networks: revealing the past of incrementally neuroevolved CNNs. GECCO '23 Companion: Companion Conference on Genetic and Evolutionary Computation, Lisbon Portugal, 14.07.2023-19.07.2023. https://doi.org/10.1145/3583133.3595848
Conference Proceeding
Neuroevolution Trajectory Networks of the Behaviour Space
Sarti S, Adair J & Ochoa G (2022) Neuroevolution Trajectory Networks of the Behaviour Space. In: Jiménez Laredo JL, Hidalgo JI & Babaagba KO (eds.) Applications of Evolutionary Computation. Lecture Notes in Computer Science, 13224. EvoApplications 2022, Madrid, Spain, 20.04.2022-22.04.2022. Cham, Switzerland: Springer International Publishing, pp. 685-703. https://doi.org/10.1007/978-3-031-02462-7_43
Article
Recombination and Novelty in Neuroevolution: A Visual Analysis
Sarti S, Adair J & Ochoa G (2022) Recombination and Novelty in Neuroevolution: A Visual Analysis. SN Computer Science, 3 (3), Art. No.: 185. https://doi.org/10.1007/s42979-022-01064-6
Conference Proceeding
A NEAT Visualisation of Neuroevolution Trajectories
Sarti S & Ochoa G (2021) A NEAT Visualisation of Neuroevolution Trajectories. In: Castillo PA & Jiménez Laredo JL (eds.) Applications of Evolutionary Computation. Lecture Notes in Computer Science, 12694. 24th International Conference, EvoApplications 2021, Seville, Spain, 07.04.2021-09.04.2021. Cham, Switzerland: Springer, pp. 714-728. https://doi.org/10.1007/978-3-030-72699-7_45
