Zobrazeno 1 - 4
of 4
pro vyhledávání: '"Pikus, Benjamin"'
Autor:
LeVine, Will, Pikus, Benjamin, Phillips, Jacob, Norman, Berk, Gil, Fernando Amat, Hendryx, Sean
As deep neural networks become adopted in high-stakes domains, it is crucial to identify when inference inputs are Out-of-Distribution (OOD) so that users can be alerted of likely drops in performance and calibration despite high confidence -- ultima
Externí odkaz:
http://arxiv.org/abs/2401.12129
Foundation models, specifically Large Language Models (LLMs), have lately gained wide-spread attention and adoption. Reinforcement Learning with Human Feedback (RLHF) involves training a reward model to capture desired behaviors, which is then used t
Externí odkaz:
http://arxiv.org/abs/2311.14743
Calibration of deep learning models is crucial to their trustworthiness and safe usage, and as such, has been extensively studied in supervised classification models, with methods crafted to decrease miscalibration. However, there has yet to be a com
Externí odkaz:
http://arxiv.org/abs/2303.12748
Publikováno v:
New Jersey Jewish News; 6/28/2024, Vol. 78 Issue 41, p19-20, 2p
