What is flagged in uncertainty quantification? latent density models for uncertainty categorization
Uncertainty quantification (UQ) is essential for creating trustworthy machine learning
models. Recent years have seen a steep rise in UQ methods that can flag suspicious …
models. Recent years have seen a steep rise in UQ methods that can flag suspicious …
Increasing trustworthiness of deep neural networks via accuracy monitoring
Z Shao, J Yang, S Ren - arXiv preprint arXiv:2007.01472, 2020 - arxiv.org
Inference accuracy of deep neural networks (DNNs) is a crucial performance metric, but can
vary greatly in practice subject to actual test datasets and is typically unknown due to the …
vary greatly in practice subject to actual test datasets and is typically unknown due to the …
[PDF][PDF] What is Flagged in Uncertainty Quantification? Latent Density Models for Uncertainty Categorization
Uncertainty quantification (UQ) is essential for creating trustworthy machine learning
models. Recent years have seen a steep rise in UQ methods that can flag suspicious …
models. Recent years have seen a steep rise in UQ methods that can flag suspicious …
Probabilistic interval prediction method based on shape‐adaptive quantile regression
This article introduces customized screening ensemble with shape‐adaptive quantile
regression (CseAQR), a novel probabilistic interval forecasting method built upon the …
regression (CseAQR), a novel probabilistic interval forecasting method built upon the …
Scalable architecture for automating machine learning model monitoring
J de la Rúa Martínez - 2020 - diva-portal.org
Last years, due to the advent of more sophisticated tools for exploratory data analysis, data
management, Machine Learning (ML) model training and model serving into production, the …
management, Machine Learning (ML) model training and model serving into production, the …
An Experimentation and Analytics Framework for {Large-Scale}{AI} Operations Platforms
This paper presents a trace-driven experimentation and analytics framework that allows
researchers and engineers to devise and evaluate operational strategies for large-scale AI …
researchers and engineers to devise and evaluate operational strategies for large-scale AI …
Scalable architecture for automating machine learning model monitoring
J Rúa Martínez - 2020 - oa.upm.es
Last years, due to the advent of more sophisticated tools for exploratory data analysis, data
management, Machine Learning (ML) model training and model serving into production, the …
management, Machine Learning (ML) model training and model serving into production, the …