Computer Science
Quantifying Distribution Shifts and Uncertainties for Enhanced Model Robustness in Machine Learning Applications
V. Flovik
This intriguing study by Vegard Flovik explores the challenges posed by distribution shifts in machine learning. Using synthetic data generated through the van der Waals equation, the research reveals innovative methods to enhance model adaptation and generalization, specifically highlighting the significance of Mahalanobis distance in improving model robustness and tackling uncertainties.
Related Publications
Explore these studies to deepen your understanding
Adjacent work that informs or extends this paper's methodology and findings.
Computer Science
The Goldilocks paradigm: comparing classical machine learning, large language models, and few-shot learning for drug discovery applications
S. H. Snyder, P. A. Vignaux, et al.
Medicine and Health
Machine Learning Model to Differentiate Between Acute Kidney Injury and Functional Decline in Children with Urinary Tract Infection
T. Cm
Earth Sciences
A machine learning paradigm for necessary observations to reduce uncertainties in aerosol climate forcing
J. Redemann and L. Gao
Medicine and Health
Predictive model of castration resistance in advanced prostate cancer by machine learning using genetic and clinical data: KYUCOG-1401-A study
M. Shiota, S. Nemoto, et al.
