Weighted envelope correlation-based waveform inversion using automatic differentiation
Full-waveform inversion (FWI) is a popularly used high-resolution seismic inversion method.
It relies on the measure of the misfit between observed data and predicted data. Due to the …
It relies on the measure of the misfit between observed data and predicted data. Due to the …
Combinatory adjoints and differentiation
We develop a compositional approach for automatic and symbolic differentiation based on
categorical constructions in functional analysis where derivatives are linear functions on …
categorical constructions in functional analysis where derivatives are linear functions on …
A versatile implicit computational framework for continuum-kinematics-inspired peridynamics
Continuum-kinematics-inspired peridynamics (CPD) has been recently proposed as a novel
reformulation of peridynamics that is characterized by one-, two-and three-neighbor …
reformulation of peridynamics that is characterized by one-, two-and three-neighbor …
LLVM code optimisation for automatic differentiation: when forward and reverse mode lead in the same direction
ME Schüle, M Springer, A Kemper… - Proceedings of the Sixth …, 2022 - dl.acm.org
Both forward and reverse mode automatic differentiation derive a model function as used for
gradient descent automatically. Reverse mode calculates all derivatives in one run, whereas …
gradient descent automatically. Reverse mode calculates all derivatives in one run, whereas …
Optimal inversion of conversion parameters from satellite AOD to ground aerosol extinction coefficient using automatic differentiation
L Li - Remote Sensing, 2020 - mdpi.com
Satellite aerosol optical depth (AOD) plays an important role for high spatiotemporal-
resolution estimation of fine particulate matter with diameters≤ 2.5 μm (PM2. 5). However …
resolution estimation of fine particulate matter with diameters≤ 2.5 μm (PM2. 5). However …
Automatic differentiation for inverse problems in X-ray imaging and microscopy
F Guzzi, A Gianoncelli, F Billè, S Carrato, G Kourousias - Life, 2023 - mdpi.com
Computational techniques allow breaking the limits of traditional imaging methods, such as
time restrictions, resolution, and optics flaws. While simple computational methods can be …
time restrictions, resolution, and optics flaws. While simple computational methods can be …
Programmation différentiable à grande échelle pour les données relationnelles
P Peseux - 2023 - theses.hal.science
Cette thèse de doctorat présente trois contributions dans le domaine de la programmation
différentiable axée sur les données relationnelles. Les données relationnelles sont …
différentiable axée sur les données relationnelles. Les données relationnelles sont …
Kotlin∇: A shape-safe DSL for differentiable programming
B Considine, M Famelis, L Paull - … for ML Workshop at NeurIPS 2019, 2019 - openreview.net
Kotlin is a statically-typed programming language with support for embedded domain
specific languages, asynchronous programming, and multi-platform compilation. In this …
specific languages, asynchronous programming, and multi-platform compilation. In this …
Coarsening optimization for differentiable programming
This paper presents a novel optimization for differentiable programming named coarsening
optimization. It offers a systematic way to synergize symbolic differentiation and algorithmic …
optimization. It offers a systematic way to synergize symbolic differentiation and algorithmic …
The Shallow Gibbs Network, Double Backpropagation and Differential Machine learning
NKA ALAHASSA - ScienceOpen Preprints, 2021 - scienceopen.com
We have built a Shallow Gibbs Network model as a Random Gibbs Network Forest to reach
the performance of the Multilayer feedforward Neural Network in a few numbers of …
the performance of the Multilayer feedforward Neural Network in a few numbers of …