Aleksandr Chebykin

Volledige naam

A. Chebykin

E-mail

Aleksandr.Chebykin@cwi.nl

Telefoon

+31 20 592 4073

Kamer

M231

Afdeling(en)

Evolutionary Intelligence

Functie(s)

PhD student

Biography

Aleksandr Chebykin did his Bachelor in Software Engineering at the faculty of Mathematics & Mechanics of the Saint Petersburg State University from 2014 to 2018. During the period of 2018-2020, he studied for the Computer Science Master's degree at the Technical University of Berlin, where he focused on Machine Learning. His Master thesis concerned learning sparse structure of neural networks that facilitated their interpretation.

Chebykin, A., Dushatskiy, A., Alderliesten, T., & Bosman, P. (2023). Shrink-Perturb improves architecture mixing during Population Based Training for Neural Architecture Search. In Proceedings of the 26th European Conference on Artificial Intelligence, ECAI 2023 (pp. 381–388). doi:10.3233/FAIA230294
Dushatskiy, A., Chebykin, A., Alderliesten, T., & Bosman, P. (2023). Multi-objective population based training. In Proceedings of the 40th International Conference on Machine Learning, PMLR (pp. 8969–8989).
Chebykin, A., Alderliesten, T., & Bosman, P. (2022). Evolutionary neural cascade search across supernetworks. In GECCO 2022 - Proceedings of the 2022 Genetic and Evolutionary Computation Conference (pp. 1038–1047). doi:10.1145/3512290.3528749

Best Paper Award in track: Neuroevolution, of GECCO 2022 (2022)

Distributed and Automated Evolutionary Deep Architecture Learning with Unprecedented Scalability (DAEDALUS)

Aleksandr Chebykin

Biography

Publications

Awards

Current projects with external funding

Aleksandr Chebykin

Biography

Publications

Awards

Current projects with external funding

Cookies