DOE OSTI · 1656637
Deep Ensemble Confidence Levels for Multi-hot Categorization
Abstract
NOICE (Neural Optical Image Categorizer for the Elog) is a small collaboration tasked with categorizing the images in the Fermilab Accelerator Division electronic logbook by using Artificial Intelligence. To do so, we manually categorized a subset of the images in the E-log into nine independent labels. Each image was then multi-hot-encoded into a nine-dimensional binary vector because each image could have more then one label.
Explore related subjects
Keep this discovery
Explore connections, maps & timelines
Leone, Giovani. 2020-08-07. Deep Ensemble Confidence Levels for Multi-hot Categorization. https://doi.org/10.2172/1656637. https://searchnasa.com/record/osti%3A1656637/deep-ensemble-confidence-levels-for-multi-hot-categorization
Citations retain the original authors and DOI and include this site’s record URL. If this discovery service contributed to your research, you can also cite Search NASA by Indiciae: BibTeX · RIS.