EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Conditional Restricted Boltzmann Machines for Class-Imbalance Mitigation: A Stable and Interpretable Framework for Targeted Data Augmentation

Vaibhav Shekar, Ananthkrishnan Chakalathalam Kannan, Shaun Sunny, Anbazhagan Mahadevan

Procedia Computer Science · 2026 · 283 · 4159-4174

DOI: 10.1016/j.procs.2026.06.476 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Procedia Computer Science, 2026. Verfasst von Vaibhav Shekar und 3 weiteren Autor:innen. Die Arbeit nennt 24 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Kein Abstract verfügbar.

Zitieren

APA

Shekar, V., Kannan, A. C., Sunny, S., & Mahadevan, A. (2026). Conditional Restricted Boltzmann Machines for Class-Imbalance Mitigation: A Stable and Interpretable Framework for Targeted Data Augmentation. Procedia Computer Science, 283, 4159-4174. https://doi.org/10.1016/j.procs.2026.06.476

Vancouver

Shekar V, Kannan AC, Sunny S, Mahadevan A. Conditional Restricted Boltzmann Machines for Class-Imbalance Mitigation: A Stable and Interpretable Framework for Targeted Data Augmentation. Procedia Computer Science. 2026;283:4159-4174. doi:10.1016/j.procs.2026.06.476

BibTeX
@article{Shekar2026,
  author = {Shekar, Vaibhav and Kannan, Ananthkrishnan Chakalathalam and Sunny, Shaun and Mahadevan, Anbazhagan},
  title = {Conditional Restricted Boltzmann Machines for Class-Imbalance Mitigation: A Stable and Interpretable Framework for Targeted Data Augmentation},
  journal = {Procedia Computer Science},
  year = {2026},
  volume = {283},
  pages = {4159--4174},
  doi = {10.1016/j.procs.2026.06.476}
}
Kostenlos starten →