Sparse wars: A survey and comparative study of spherical deconvolution algorithms for diffusion MRI

Chat with Graph Search

Ask any question about EPFL courses, lectures, exercises, research, news, etc. or try the example questions below.

DISCLAIMER: The Graph Chatbot is not programmed to provide explicit or categorical answers to your questions. Rather, it transforms your questions into API requests that are distributed across the various IT services officially administered by EPFL. Its purpose is solely to collect and recommend relevant references to content that you can explore to help you answer your questions.

The remarkable ability of deep learning (DL) models to approximate high-dimensional functions from samples has sparked a revolution across numerous scientific and industrial domains that cannot be overemphasized. In sensitive applications, the good perform ...

Catastrophic overfitting (CO) in single-step adversarial training (AT) results in abrupt drops in the adversarial test accuracy (even down to 0%). For models trained with multi-step AT, it has been observed that the loss function behaves locally linearly w ...

In inverse problems, the task is to reconstruct an unknown signal from its possibly noise-corrupted measurements. Penalized-likelihood-based estimation and Bayesian estimation are two powerful statistical paradigms for the resolution of such problems. They ...

This paper studies kernel ridge regression in high dimensions under covariate shifts and analyzes the role of importance re-weighting. We first derive the asymptotic expansion of high dimensional kernels under covariate shifts. By a bias-variance decomposi ...

In this thesis, we study two closely related directions: robustness and generalization in modern deep learning. Deep learning models based on empirical risk minimization are known to be often non-robust to small, worst-case perturbations known as adversari ...

Herein, machine learning (ML) models using multiple linear regression (MLR), support vector regression (SVR), random forest (RF) and artificial neural network (ANN) are developed and compared to predict the output features viz. specific capacitance (Csp), ...

We consider the problem of learning a target function corresponding to a deep, extensive-width, non-linear neural network with random Gaussian weights. We consider the asymptotic limit where the number of samples, the input dimension and the network width ...

In this paper, we investigate the impact of stochasticity and large stepsizes on the implicit regularisation of gradient descent (GD) and stochastic gradient descent (SGD) over diagonal linear networks. We prove the convergence of GD and SGD with macroscop ...

In this paper we fully describe the trajectory of gradient flow over diagonal linear networks in the limit of vanishing initialisation. We show that the limiting flow successively jumps from a saddle of the training loss to another until reaching the minim ...

The emergence of deep-learning-based methods to solve image-reconstruction problems has enabled a significant increase in quality. Unfortunately, these new methods often lack reliability and explainability, and there is a growing interest to address these ...

In this dissertation, we propose multiple methods to improve transfer learning for pretrained language models (PLMs). Broadly, transfer learning is a powerful technique in natural language processing, where a language model is first pre-trained on a data-r ...

Background: A neurocognitive phenotype of post-COVID-19 infection has recently been described that is characterized by a lack of awareness of memory impairment (i.e., anosognosia), altered functional connectivity in the brain's default mode and limbic netw ...

We propose two deep learning models that fully automate shape parameterization for aerodynamic shape optimization. Both models are optimized to parameterize via deep geometric learning to embed human prior knowledge into learned geometric patterns, elimina ...

Deep Neural Networks (DNNs) have obtained impressive performance across tasks, however they still remain as black boxes, e.g., hard to theoretically analyze. At the same time, Polynomial Networks (PNs) have emerged as an alternative method with a promising ...

Very preterm (VPT) young adolescents are at high risk of executive, behavioural and socio-emotional difficulties. Previous research has shown significant evidence of the benefits of mindfulness-based intervention (MBI) on these abilities. This study aims t ...

Neural machine translation (MT) and text generation have recently reached very high levels of quality. However, both areas share a problem: in order to reach these levels, they require massive amounts of data. When this is not present, they lack generaliza ...

The Obukhov-Corrsin theory of scalar turbulence [21, 54] advances quantitative predictions on passive-scalar advection in a turbulent regime and can be regarded as the analogue for passive scalars of Kolmogorov's K41 theory of fully developed turbulence [4 ...

Deep neural networks have become ubiquitous in today's technological landscape, finding their way in a vast array of applications. Deep supervised learning, which relies on large labeled datasets, has been particularly successful in areas such as image cla ...

The motor learning process entails plastic changes in the brain, especially in brain network reconfigurations. In the current study, we sought to characterize motor learning by determining changes in the coupling behaviour between the brain functional and ...

Sparse wars: A survey and comparative study of spherical deconvolution algorithms for diffusion MRI

Chat with Graph Search

Towards Trustworthy Deep Learning for Image Reconstruction

Efficient local linearity regularization to overcome catastrophic overfitting

Statistical Inference for Inverse Problems: From Sparsity-Based Methods to Neural Networks

High-Dimensional Kernel Methods under Covariate Shift: Data-Dependent Implicit Regularization

Understanding generalization and robustness in modern deep learning

Machine learning models for prediction of electrochemical properties in supercapacitor electrodes using MXene and graphene nanoplatelets

Bayes-optimal Learning of Deep Random Networks of Extensive-width

(S)GD over Diagonal Linear Networks: Implicit Regularisation, Large Stepsizes and Edge of Stability

Saddle-to-Saddle Dynamics in Diagonal Linear Networks

A Neural-Network-Based Convex Regularizer for Inverse Problems

Improving Generalization of Pretrained Language Models

Acute TNF alpha levels predict cognitive impairment 6-9 months after COVID-19 infection

Automatic Parameterization for Aerodynamic Shape Optimization via Deep Geometric Learning

Regularization of polynomial networks for image recognition

The effect of mindfulness-based intervention on neurobehavioural functioning and its association with white-matter microstructural changes in preterm young adolescents

Regularization Techniques for Low-Resource Machine Translation

Regularization of polynomial networks for image recognition

Anomalous Dissipation and Lack of Selection in the Obukhov-Corrsin Theory of Scalar Turbulence

Deep Learning Generalization with Limited and Noisy Labels

Brain connectome correlates of short-term motor learning in healthy older subjects