Benchmarking uncertainty quantification for protein engineering. [PDF]
PLoS Computational BiologyMachine learning sequence-function models for proteins could enable significant advances in protein engineering, especially when paired with state-of-the-art methods to select new sequences for property optimization and/or model improvement. Such methods
Kevin P Greenman +2 more
doaj +2 more sources
Generating with Confidence: Uncertainty Quantification for Black-box Large Language Models [PDF]
Trans. Mach. Learn. Res., 2023 Large language models (LLMs) specializing in natural language generation (NLG) have recently started exhibiting promising capabilities across a variety of domains.
Zhen Lin, Shubhendu Trivedi, Jimeng Sun
semanticscholar +1 more source
How is a global sensitivity analysis of a catchment-scale, distributed pesticide transfer model performed? Application to the PESHMELBA model [PDF]
Geoscientific Model Development, 2023 Pesticide transfers in agricultural catchments are responsible for diffuse but major risks to water quality. Spatialized pesticide transfer models are useful tools to assess the impact of the structure of the landscape on water quality.
E. Rouzies +3 more
doaj +1 more source
Research on application method of uncertainty quantification technology in equipment test identification [PDF]
MATEC Web of Conferences, 2021 This paper introduces the concepts of equipment test qualification and uncertainty quantification, and the analysis framework and process of equipment test uncertainty quantification.
Wang Jiajia +3 more
doaj +1 more source
Machine Learning With Data Assimilation and Uncertainty Quantification for Dynamical Systems: A Review [PDF]
IEEE/CAA Journal of Automatica Sinica, 2023 Data assimilation (DA) and uncertainty quantification (UQ) are extensively used in analysing and reducing error propagation in high-dimensional spatial-temporal dynamics. Typical applications span from computational fluid dynamics (CFD) to geoscience and
Sibo Cheng +16 more
semanticscholar +1 more source
Shifting Attention to Relevance: Towards the Predictive Uncertainty Quantification of Free-Form Large Language Models [PDF]
Annual Meeting of the Association for Computational Linguistics, 2023 Large Language Models (LLMs) show promising results in language generation and instruction following but frequently"hallucinate", making their outputs less reliable.
Jinhao Duan +7 more
semanticscholar +1 more source
loopUI-0.1: indicators to support needs and practices in 3D geological modelling uncertainty quantification [PDF]
Geoscientific Model Development, 2022 To support the needs of practitioners regarding 3D geological modelling and uncertainty quantification in the field, in particular from the mining industry, we propose a Python package called loopUI-0.1 that provides a set of local and global indicators ...
G. Pirot +13 more
doaj +1 more source
Bayes' Rays: Uncertainty Quantification for Neural Radiance Fields [PDF]
Computer Vision and Pattern Recognition, 2023 Neural Radiance Fields (NeRFs) have shown promise in applications like view synthesis and depth estimation, but learning from multiview images faces inherent uncertain-ties.
Lily Goli +4 more
semanticscholar +1 more source
Impact of ploidy and pathogen life cycle on resistance durability
Peer Community Journal, 2021 The breeding of resistant hosts based on the gene-for-gene interaction is crucial to address epidemics of plant pathogens in agroecosystems. Resistant host deployment strategies are developed and studied worldwide to decrease the probability of ...
Saubin, Méline +4 more
doaj +1 more source
Latent diffusion models for generative precipitation nowcasting with accurate uncertainty quantification [PDF]
arXiv.org, 2023 Diffusion models have been widely adopted in image generation, producing higher-quality and more diverse samples than generative adversarial networks (GANs).
J. Leinonen +4 more
semanticscholar +1 more source