EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC-SA 4.0

Evaluation of novel AI architectures for uncertainty estimation

Erik Pautsch, John Li, Silvio Rizzi, George K. Thiruvathukal, Maria Pantoja

Revista Colombiana de Computación · 31.12.2024 · 25 (2) · 23-34

DOI: 10.29375/25392115.5274 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Revista Colombiana de Computación, online erschienen am 31.12.2024. Verfasst von Erik Pautsch und 4 weiteren Autor:innen. Die Arbeit nennt 18 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-SA 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Deep learning (DL) has advanced computer vision, delivering impressive performance on intricate visual tasks. Yet, the need for accurate uncertainty estimations, particularly for out-of-distribution (OOD) inputs, persists. Our research evaluates uncertainty in Convolutional Neural Networks (CNN) and Vision Transformers (ViT) using the MNIST and ImageNet-1K datasets. Using High-Performance (HPC) platforms, including the traditional Polaris supercomputer and AI accelerators like Cerebras CS-2 and SambaNova DataScale, we assessed the computational merits and bottlenecks of each platform. This paper delineates key considerations for using HPC in uncertainty estimations in DL, offering insights that guide the integration of algorithms and hardware for robust DL applications, especially in computer vision.

Zitieren

APA

Pautsch, E., Li, J., Rizzi, S., Thiruvathukal, G. K., & Pantoja, M. (2024). Evaluation of novel AI architectures for uncertainty estimation. Revista Colombiana de Computación, 25(2), 23-34. https://doi.org/10.29375/25392115.5274

Vancouver

Pautsch E, Li J, Rizzi S, Thiruvathukal GK, Pantoja M. Evaluation of novel AI architectures for uncertainty estimation. Revista Colombiana de Computación. 2024;25(2):23-34. doi:10.29375/25392115.5274

BibTeX
@article{Pautsch2024,
  author = {Pautsch, Erik and Li, John and Rizzi, Silvio and Thiruvathukal, George K. and Pantoja, Maria},
  title = {Evaluation of novel AI architectures for uncertainty estimation},
  journal = {Revista Colombiana de Computación},
  year = {2024},
  volume = {25},
  number = {2},
  pages = {23--34},
  doi = {10.29375/25392115.5274}
}
Kostenlos starten →