The DOI displayed above is for this specific version of this dataset, which is currently the latest. Newer versions may be published in the future. For a link that will always point to the latest version, please use
DOI: 10.4121/732d2ec8-6a24-4619-8a22-c7d286dce5d2

Chebykin, Aleksandr (2025): Code underlying the PhD thesis: Efficient Evolutionary Hyperparameter Optimization for Deep Learning. Version 1. 4TU.ResearchData. dataset. https://doi.org/10.4121/732d2ec8-6a24-4619-8a22-c7d286dce5d2.v1

Categories

• Artificial Intelligence and Image Processing
• Information and Computing Sciences

Keywords

Deep Learning Deep Reinforcement Learning (DRL) Evolutionary Algorithms Hyperparameter Tuning

Licence

CC BY-NC-SA 4.0

Interoperability

• RO-Crate Metadata

Export as...

RefWorks BibTeX Reference Manager Endnote DataCite NLM DC CFF

by Aleksandr Chebykin

Code underlying the PhD thesis: Efficient Evolutionary Hyperparameter Optimization for Deep Learning. As the focus of the thesis is on hyperparameter optimization, code for the algorithms developed during the PhD research are included, namely ENCAS, PBT-NAS, IPBT, HyFree-S3, as well as code for comparing and evaluating previously existing PBT variants. A general readme file is included, as well as code directories, one per chapter/project, each containing its own readme file with instructions on reproducing the experiments.

History

• 2025-11-10 first online, published, posted

Publisher

4TU.ResearchData

Format

script/.py

Funding

• NWO Open Technology Programme (grant code 18373) NWO

Organizations

TU Delft, Faculty of Electrical Engineering, Mathematics and Computer Science, Department of Software Technology
Centrum Wiskunde & Informatica - CWI
Leiden University Medical Center - LUMC