Publications related to Inverse Rendering for PET Image Reconstruction

Related publications (16)

Time-resolved, physics-informed neural networks for tokamak total emission reconstruction and modelling

Diagnostics play a pivotal role in nuclear fusion experimental reactors, supporting physical studies, modelling, and plasma control. However, most diagnostics provide limited and partial information about the plasma's status. For instance, magnetic probes ...

IOP Publishing Ltd2025

Split weight distribution learning for binary neural networks exploiting nano-memristive graphene/sumanene/graphene devices

Alexandre Schmid

Research in artificial intelligence (AI) and neural network (NN) technologies has been boosted by recent hardware advances, while the emergence of self-synthesized materials such as nanocarbons has attracted much attention to overcome the limitations of Si ...

IOP Publishing Ltd2025

What can be learnt with wide convolutional neural networks?

Matthieu Wyart, Alessandro Favero, Francesco Cagnetta

Understanding how convolutional neural networks (CNNs) can efficiently learn high-dimensional functions remains a fundamental challenge. A popular belief is that these models harness the local and hierarchical structure of natural data such as images. Yet, ...

2024

A graph convolutional autoencoder approach to model order reduction for parametrized PDEs

Jan Sickmann Hesthaven, Federico Pichi

The present work proposes a framework for nonlinear model order reduction based on a Graph Convolutional Autoencoder (GCA-ROM). In the reduced order modeling (ROM) context, one is interested in obtaining real -time and many-query evaluations of parametric ...

Academic Press Inc Elsevier Science2024

Fast and robust parameter estimation with uncertainty quantification for the cardiac function

Alfio Quarteroni

Background and objectives: Parameter estimation and uncertainty quantification are crucial in computa-tional cardiology, as they enable the construction of digital twins that faithfully replicate the behavior of physical patients. Many model parameters reg ...

ELSEVIER IRELAND LTD2023

Polynomial-time universality and limitations of deep learning

Emmanuel Abbé

The goal of this paper is to characterize function distributions that general neural networks trained by descent algorithms (GD/SGD), can or cannot learn in polytime. The results are: (1) The paradigm of general neural networks trained by SGD is poly-time ...

WILEY2023

Adversarial training with informed data selection

Pascal Frossard, Javier Alejandro Maroto Morales

With the increasing amount of available data and advances in computing capabilities, deep neural networks (DNNs) have been successfully employed to solve challenging tasks in various areas, including healthcare, climate, and finance. Nevertheless, state-of ...

IEEE2022

NeuroMechFly, a neuromechanical model of adult Drosophila melanogaster

Auke Ijspeert, Pavan P Ramdya, Jonathan Patrick Arreguit O'Neill, Shravan Tata Ramalingasetty, Victor Lobato Rios, Pembe Gizem Ozdil

Animal behavior emerges from an interaction between neural network dynamics, musculoskeletal properties and the physical environment. Accessing and understanding the interplay between these elements requires the development of integrative and morphological ...

Nature Publishing Group2022

Evaluating reproducibility and subject-specificity of microstructure-informed connectivity

Jean-Philippe Thiran, Tobias Kober, Elda Fischi Gomez, Tom Hilbert, Elena Beanato, Gabriel Girard, Julia Brügger, Gian Franco Piredda, Friedhelm Christoph Hummel, Takuya Morishita, Maximilian Jonas Wessel, Philipp Johannes Koch, Erick Jorge Canales Rodriguez, Marco Pizzolato, Andéol Geoffroy Cadic-Melchior, Chang-Hyun Park

Tractography enables identifying and evaluating the healthy and diseased brain's white matter pathways from diffusion-weighted magnetic resonance imaging data. As previous evaluation studies have reported significant false-positive estimation biases, recen ...

ACADEMIC PRESS INC ELSEVIER SCIENCE2022

Micromechanically inspired investigation of cemented granular materials: part I-from X-ray micro tomography to measurable model variables

Edward Carlo Giorgio Andò

Cemented granular materials are abundant in nature and are often artificially produced. Their macroscopic behaviour is driven by small-scale material processes, which are generally classified as: grain breakage, cement damage and fragment rearrangement. Th ...

SPRINGER HEIDELBERG2022

PM2.5 Monitoring: Use Information Abundance Measurement and Wide and Deep Learning

Daniel Thalmann

This article devises a photograph-based monitoring model to estimate the real-time PM2.5 concentrations, overcoming currently popular electrochemical sensor-based PM2.5 monitoring methods' shortcomings such as low-density spatial distribution and time dela ...

IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC2021

State of the Art on Computational Design of Assemblies with Rigid Parts

Mark Pauly, Ziqi Wang, Peng Song

An assembly refers to a collection of parts joined together to achieve a specific form and/or functionality. Designing assemblies is a non-trivial task as a slight local modification on a part's geometry or its joining method could have a global impact on ...

WILEY2021

Neurovascular stent artifacts in 3D-TOF and 3D-PCMRI: Influence of stent design on flow measurement

Mohamed Farhat, Pierre Bouillot

Purpose: The morphological and hemodynamic evaluations of neurovascular diseases treated with stents would benefit from noninvasive imaging techniques such as 3D time-of-flight MRI (3D-TOF) and 3D phase contrast MRI (3D-PCMRI). For this purpose, a comprehe ...

WILEY2019

Robustness of Classifiers to Universal Perturbations: A Geometric Perspective

Pascal Frossard, Alhussein Fawzi, Seyed Mohsen Moosavi Dezfooli

Deep networks have recently been shown to be vulnerable to universal perturbations: there exist very small image-agnostic perturbations that cause most natural images to be misclassified by such classifiers. In this paper, we provide a quantitative analysi ...

2018

Mixed-precision architecture based on computational memory for training deep neural networks

Irem Boybat Kara, Abu Sebastian

Deep neural networks (DNN) have revolutionized the field of machine learning by providing unprecedented human-like performance in solving many real-world problems such as image or speech recognition. Training of large DNNs, however, is a computationally in ...

IEEE2018

Comparing human and machine performances in transcribing 18th century handwritten Venetian script

Frédéric Kaplan, Sofia Ares Oliveira

Automatic transcription of handwritten texts has made important progress in the recent years. This increase in performance, essentially due to new architectures combining convolutional neural networks with recurrent neutral networks, opens new avenues for ...

2018