Metraipolis › archive › dc_5ffecf9ef319
Investigating Hyperparameter Optimization and Transferability for ES-HyperNEAT: A TPE Approach — arXiv:2609.00449
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.00449
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-17T06:33:22.526Z
- SHA-256 of the archived text
84f912c7cc15dca86b33fd5f3281c82cd78500a36c1473182b0e089c44b97282- Stable URL of this page
https://metraipolis.com/documento/dc_5ffecf9ef319
How to cite
Investigating Hyperparameter Optimization and Transferability for ES-HyperNEAT: A TPE Approach — arXiv:2609.00449 — arXiv (en), https://arxiv.org/abs/2609.00449 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_5ffecf9ef319 (Metraipolis archive dc_5ffecf9ef319, sha256 84f912c7cc15dca86b33fd5f3281c82cd78500a36c1473182b0e089c44b97282)
BibTeX
@misc{dc5ffecf9ef319,
title = {Investigating Hyperparameter Optimization and Transferability for ES-HyperNEAT: A TPE Approach — arXiv:2609.00449},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.00449},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_5ffecf9ef319; sha256 84f912c7cc15dca86b33fd5f3281c82cd78500a36c1473182b0e089c44b97282},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.00449. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Neuroevolution of Augmenting Topologies (NEAT) and its advanced version, Evolvable-Substrate HyperNEAT (ES-HyperNEAT), have shown great potential in developing neural networks. However, their effectiveness heavily depends on the selection of hyperparameters. This study investigates the optimization of ES-HyperNEAT hyperparameters using the Tree-structured Parzen Estimator (TPE) on the MNIST classification task, exploring a search space of over 3 billion potential combinations. TPE effectively navigates this vast space, significantly outperforming random search in terms of mean, median, and best accuracy. During the validation process, the best hyperparameter configuration found by TPE achieves an accuracy of 29.00% on MNIST, surpassing previous studies while using a smaller population size and fewer generations. The transferability of the optimized hyperparameters is explored in logic operations and Fashion-MNIST tasks, revealing successful transfer to the more complex Fashion-MNIST problem but limited to simpler logic operations. This study emphasizes a method to unlock the full potential of neuroevolutionary algorithms and provides insights into the hyperparameters' transferability across tasks of varying complexity. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-02 in cs.AI). Categorie arXiv: Neural and Evolutionary Computing (cs.NE) ; Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2609.00449 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-17T06:15:12.782Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-02?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).