Learning Data Triage: Linear Decoding Works for Compressive 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.

One major challenge in distributed learning is to efficiently learn for each client when the data across clients is heterogeneous or non i.i.d (not independent or identically distributed). This provides a significant challenge as the data of the other clie ...

Emission Line Galaxies (ELGs) are one of the main tracers that the Dark Energy Spectroscopic Instrument (DESI) uses to probe the universe. However, they are afflicted by strong spurious correlations between target density and observing conditions known as ...

Pulse-Echo Ultrasound Imaging suffers from several sources of image degradation. In clinical conditions, superficial layers made of different tissues (e.g. skin, fat or muscles) create aberrations that can severely deteriorate image quality. To correct suc ...

Constrained Spherical Deconvolution (CSD) is a state-of-the-art technique for unraveling complex fiber configurations of white matter from diffusion MRI data. Despite its ability to identify multiple fiber orientations, it faces difficulties in resolving f ...

We introduce the concept of "universal"password model - a password model that, once pre-trained, can automatically adapt its guessing strategy based on the target system. To achieve this, the model does not need to access any plaintext passwords from the t ...

The development of biophysical models for clinical applications is rapidly advancing in the research community, thanks to their predictive nature and their ability to assist the interpretation of clinical data. However, high-resolution and accurate multi-p ...

Compressed Sensing teaches us that measurements can be traded for offline computation if the signal being sensed has a simple enough representation. Proper decoders can exactly recover the high-dimensional signal of interest from a lower-dimensional vector ...

This thesis focuses on developing efficient algorithmic tools for processing large datasets. In many modern data analysis tasks, the sheer volume of available datasets far outstrips our abilities to process them. This scenario commonly arises in tasks incl ...

One of the greatest challenges in the design of modern wearable devices is energy efficiency. While data processing and communication have received a lot of attention from the industry and academia, leading to highly efficient microcontrollers and transmis ...

Purpose MP2RAGE T-1-weighted imaging has been shown to be beneficial for various applications, mainly because of its good grey-white matter contrast, its B-1-robustness and ability to derive T(1)maps. Even using parallel imaging, the method requires long a ...

We experimentally demonstrate Kramers-Kronig detection of four 20 Gbaud 16-quadrature-amplitude-modulated (QAM) channels after 50 km fiber transmission using two soliton Kerr combs as signal sources and local oscillators. The estimated carrier phase at the ...

The theory underlying robust distributed learning algorithms, designed to resist adversarial machines, matches empirical observations when data is homogeneous. Under data heterogeneity however, which is the norm in practical scenarios, established lower bo ...

Magnetic resonance resonance (MRI) is a widely used modality to obtain in vivo tissue information. Clinical applications are near countless, and almost all body parts can be examined using an MR scanner. As the method is non invasive, does not use ionizing ...

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 vibrational response of solid materials and structural components is substantially governed by their mechanical and geometrical properties. Low-frequency vibrations and modal frequencies are sensitive to global geometrical deviations, while high-freque ...

Whether in factory or household scenarios, rhythmic movements play a crucial role in many daily-life tasks. In this paper we propose a Fourier movement primitive (FMP) representation to learn such type of skills from human demonstrations. Our approach take ...

Scanning transmission X-ray microscopy (STXM) produces images in which each pixel value is related to the measured attenuation of an X-ray beam. In practice, the location of the illuminated region does not exactly match the desired uniform pixel grid. This ...

We experimentally demonstrate three-fold wavelength multicasting of a 64-quadrature-amplitude-modulation (QAM), 120-Gbit/s data channel using a microresonator Kerr frequency comb and nonlinear wave mixing. The multicasting is achieved with a data signal an ...

Purpose To obtain whole-brain high-resolution T-2 maps in 2 minutes by combining simultaneous multislice excitation and low-power PINS (power independent of number of slices) refocusing pulses with undersampling and a model-based reconstruction. Methods A ...

Reconstructing continuous signals based on a small number of discrete samples is a fundamental problem across science and engineering. We are often interested in signals with "simple" Fourier structure - e.g., those involving frequencies within a bounded r ...

Learning Data Triage: Linear Decoding Works for Compressive MRI

Chat with Graph Search

Data Heterogeneity in Linear Distributed Estimation and Learning

Mitigating imaging systematics for DESI 2024 emission Line Galaxies and beyond

A Path-Based Model for Aberration Correction in Ultrasound Imaging

Spatial Prior Informed Constrained Spherical Deconvolution in Super Resolution Variation

Universal Neural-Cracking-Machines: Self-Configurable Password Models from Auxiliary Data

Physics-informed neural network estimation of material properties in soft tissue nonlinear biomechanical models

On the optimal sampling design for the Graph Total Variation decoder: recovering piecewise-constant graph signals from a few vertex measurements

Fourier Sampling in Signal Processing and Numerical Linear Algebra

An Event-Based System for Low-Power ECG QRS Complex Detection

Accelerated MP2RAGE imaging using Cartesian phyllotaxis readout and compressed sensing reconstruction

Kramers Kronig detection of four 20 Gbaud 16-QAM channels using Kerr combs for a shared phase estimation

Robust Distributed Learning: Tight Error Bounds and Breakdown Point under Data Heterogeneity

Fat navigators based retrospective motion correction strategies for brain magnetic resonance imaging

Regularization Techniques for Low-Resource Machine Translation

Vibrational NDT with Under-sampled Data through Physics-informed Neural Networks

Fourier movement primitives: an approach for learning rhythmic robot skills from demonstrations

Hessian Splines For Scanning Transmission X-Ray Microscopy

Experimental demonstration of three-fold wavelength multicasting of a 64-QAM 120 Gbit/s data channel using a Kerr frequency comb and nonlinear wave mixing

Fast model-based T-2 mapping using SAR-reduced simultaneous multislice excitation

A Universal Sampling Method for Reconstructing Signals with Simple Fourier Transforms