3 citations · 9 across the 12 of their papers we have counts for
12 papers
Fuzzy PyTorch: Rapid Numerical Variability Evaluation for Deep Learning Models
Inés Gonzalez-Pepe, Hiba Akhaddar, Tristan Glatard +1
We introduce Fuzzy PyTorch, a framework for rapid evaluation of numerical variability in deep learning (DL) models. As DL is increasingly applied to diverse tasks, understanding va…
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…
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…
Numerical Uncertainty in Linear Registration: An Experimental Study
Niusha Mirhakimi, Yohan Chatelain, Tristan Glatard +1
While linear registration is a critical step in MRI preprocessing pipelines, its numerical uncertainty is understudied. Using Monte-Carlo Arithmetic (MCA) simulations, we assessed…
An Analysis of Performance Bottlenecks in MRI Pre-Processing
Mathieu Dugré, Yohan Chatelain, Tristan Glatard
Magnetic Resonance Image (MRI) pre-processing is a critical step for neuroimaging analysis. However, the computational cost of MRI pre-processing pipelines is a major bottleneck fo…
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…
A numerical variability approach to results stability tests and its application to neuroimaging
Yohan Chatelain, Loïc Tetrel, Christopher J. Markiewicz +5
Ensuring the long-term reproducibility of data analyses requires results stability tests to verify that analysis results remain within acceptable variation bounds despite inevitabl…
Numerical Stability of DeepGOPlus Inference
Inés Gonzalez Pepe, Yohan Chatelain, Gregory Kiar +1
Convolutional neural networks (CNNs) are currently among the most widely-used deep neural network (DNN) architectures available and achieve state-of-the-art performance for many pr…
PyTracer: Automatically profiling numerical instabilities in Python
Yohan Chatelain, Nigel Yong, Gregory Kiar +1
Numerical stability is a crucial requirement of reliable scientific computing. However, despite the pervasiveness of Python in data science, analyzing large Python programs remains…
Data Augmentation Through Monte Carlo Arithmetic Leads to More Generalizable Classification in Connectomics
Gregory Kiar, Yohan Chatelain, Ali Salari +2
Machine learning models are commonly applied to human brain imaging datasets in an effort to associate function or structure with behaviour, health, or other individual phenotypes.…
Accurate simulation of operating system updates in neuroimaging using Monte-Carlo arithmetic
Ali Salari, Yohan Chatelain, Gregory Kiar +1
Operating system (OS) updates introduce numerical perturbations that impact the reproducibility of computational pipelines. In neuroimaging, this has important practical implicatio…
Reducing numerical precision preserves classification accuracy in Mondrian Forests
Marc Vicuna, Martin Khannouz, Gregory Kiar +2
Mondrian Forests are a powerful data stream classification method, but their large memory footprint makes them ill-suited for low-resource platforms such as connected objects. We e…