3 papers
cs.LG2026
Conservative & Aggressive NaNs Accelerate U-Nets for Neuroimaging
Inés Gonzalez-Pepe, Vinuyan Sivakolunthu, Jacob Fortin +2
Deep learning models for neuroimaging increasingly rely on large architectures, making efficiency a persistent concern despite advances in hardware. Through an analysis of numerica…
math.NA2025
Uncertain but Useful: Leveraging CNN Training Variability into Data Augmentation
Inés Gonzalez-Pepe, Vinuyan Sivakolunthu, Yohan Chatelain +1
Deep learning (DL) has transformed neuroimaging by delivering state-of-the-art performance with reduced computation times. Yet, the numerical uncertainty inherent to DL training re…
eess.IV2023
Numerical Uncertainty of Convolutional Neural Networks Inference for Structural Brain MRI Analysis
Inés Gonzalez Pepe, Vinuyan Sivakolunthu, Hae Lang Park +2
This paper investigates the numerical uncertainty of Convolutional Neural Networks (CNNs) inference for structural brain MRI analysis. It applies Random Rounding -- a stochastic ar…