Partition of unity networks: deep hp-approximation

K Lee, NA Trask, RG Patel, MA Gulian… - arXiv preprint arXiv …, 2021 - arxiv.org
Approximation theorists have established best-in-class optimal approximation rates of deep
neural networks by utilizing their ability to simultaneously emulate partitions of unity and …

Train like a (Var) Pro: Efficient training of neural networks with variable projection

E Newman, L Ruthotto, J Hart… - SIAM Journal on …, 2021 - SIAM
Deep neural networks (DNNs) have achieved state-of-the-art performance across a variety
of traditional machine learning tasks, eg, speech recognition, image classification, and …

slimTrain---A Stochastic Approximation Method for Training Separable Deep Neural Networks

E Newman, J Chung, M Chung, L Ruthotto - SIAM Journal on Scientific …, 2022 - SIAM
Deep neural networks (DNNs) have shown their success as high-dimensional function
approximators in many applications; however, training DNNs can be challenging in general …

A memory-efficient self-supervised dynamic image reconstruction method using neural fields

L Lozenski, MA Anastasio, U Villa - IEEE Transactions on …, 2022 - ieeexplore.ieee.org
Dynamic imaging is essential for analyzing various biological processes but faces two main
challenges: data incompleteness and computational burden. For many imaging systems …

Online Learning Under A Separable Stochastic Approximation Framework

M Gan, X Su, G Chen, J Chen… - IEEE Transactions on …, 2024 - ieeexplore.ieee.org
We propose an online learning algorithm tailored for a class of machine learning models
within a separable stochastic approximation framework. The central idea of our approach is …

A Memory-Efficient Dynamic Image Reconstruction Method using Neural Fields

L Lozenski, MA Anastasio, U Villa - arXiv preprint arXiv:2205.05585, 2022 - arxiv.org
Dynamic imaging is essential for analyzing various biological systems and behaviors but
faces two main challenges: data incompleteness and computational burden. For many …

Neural fields for dynamic imaging

L Lozenski, M Anastasio, U Villa - Medical Imaging 2022 …, 2022 - spiedigitallibrary.org
Dynamic imaging systems monitor physiological processes that evolve or change over time.
However, image reconstruction from dynamic data is made difficult by data incompleteness …

Hospital Length of Stay Prediction with Ensemble Learning Methode

DP Hapsari, W Lumandi… - Journal of Applied …, 2023 - ejurnal.itats.ac.id
The hospital length of stay (LoS) is the number of days an inpatient will stay in the hospital.
LoS is used as a measure of hospital performance so they can improve the quality of service …

[PDF][PDF] Designing convergent and structure preserving architectures for SciML.

NA Trask - 2021 - osti.gov
Designing convergent and structure preserving architectures for SciML Page 1 Sandia National
Laboratories is a multimission laboratory managed and operated by National Technology and …

[PDF][PDF] Partition of unity networks: deep hp-approximation.

NA Trask - 2021 - osti.gov
Partition of unity networks: deep hp-approximation Page 1 Sandia National Laboratories is a
multimission laboratory managed and operated by National Technology and Engineering …