Related papers: Regularized brain reading with shrinkage and smoot…

Randomized smoothing is a technique for providing provable robustness guarantees against adversarial attacks while making minimal assumptions about a classifier. This method relies on taking a majority vote of any base classifier over…

We adapt structural complexity analysis to three-dimensional signals, with an emphasis on brain magnetic resonance imaging (MRI). This framework captures the multiscale organization of volumetric data by coarse-graining the signal at…

Denoising score matching plays a pivotal role in the performance of diffusion-based generative models. However, the empirical optimal score--the exact solution to the denoising score matching--leads to memorization, where generated samples…

In this work, we investigate a recently proposed regularization technique based on multi-branch architectures, called Shake-Shake regularization, for the task of speech emotion recognition. In addition, we also propose variants to…

Neural Radiance Fields (NeRF) has emerged as a compelling framework for scene representation and 3D recovery. To improve its performance on real-world data, depth regularizations have proven to be the most effective ones. However, depth…

Functional Magnetic Resonance Imaging (fMRI) is a powerful non-invasive tool for localizing and analyzing brain activity. This study focuses on one very important aspect of the functional properties of human brain, specifically the…

The continuous interaction between brain regions "at rest" defines the so-called resting state networks (RSN) which can be reconstructed from the analysis of functional magnetic resonance imaging (fMRI) data. What dynamical mechanism allows…

Studying learning-related plasticity is central to understanding the acquisition of complex skills, for example learning to master a musical instrument. Over the past three decades, conventional group-based functional magnetic resonance…

Resting-state functional magnetic resonance imaging (rs-fMRI) can reflect spontaneous neural activities in brain and is widely used for brain disorder analysis.Previous studies propose to extract fMRI representations through diverse…

Recent medical imaging studies have given rise to distinct but inter-related datasets corresponding to multiple experimental tasks or longitudinal visits. Standard scalar-on-image regression models that fit each dataset separately are not…

Due to the low signal-to-noise ratio and limited resolution of functional MRI data, and the high complexity of natural images, reconstructing a visual stimulus from human brain fMRI measurements is a challenging task. In this work, we…

Deep neural networks exploiting millions of parameters are nowadays the norm in deep learning applications. This is a potential issue because of the great amount of computational resources needed for training, and of the possible loss of…

While shrinkage is essential in high-dimensional settings, its use for low-dimensional regression-based prediction has been debated. It reduces variance, often leading to improved prediction accuracy. However, it also inevitably introduces…

Recently, fluorescence-based optical techniques have emerged as a powerful tool to probe information in the mammalian brain. However, tissue heterogeneities prevent clear imaging of deep neuron bodies due to light scattering. While several…

The density estimation is one of the core problems in statistics. Despite this, existing techniques like maximum likelihood estimation are computationally inefficient due to the intractability of the normalizing constant. For this reason an…

Trustworthy machine learning necessitates meticulous regulation of model reliance on non-robust features. We propose a framework to delineate and regulate such features by attributing model predictions to the input. Within our approach,…

Sparsity promoting norms are frequently used in high dimensional regression. A limitation of such Lasso-type estimators is that the optimal regularization parameter depends on the unknown noise level. Estimators such as the concomitant…

B-spline models are a powerful way to represent scientific data sets with a functional approximation. However, these models can suffer from spurious oscillations when the data to be approximated are not uniformly distributed. Model…

Despite huge successes on a wide range of tasks, neural networks are known to sometimes struggle to generalise to unseen data. Many approaches have been proposed over the years to promote the generalisation ability of neural networks,…

This thesis is dedicated to the statistical analysis of multi-sub ject fMRI data, with the purpose of identifying bain structures involved in certain cognitive or sensori-motor tasks, in a reproducible way across sub jects. To overcome…