Results 31 to 40 of about 93,812 (304)
Introduction to Automatic Differentiation [PDF]
PAMM, 2003 AbstractAutomatic, or algorithmic, differentiation (AD) is a chain rule‐based technique for evaluating derivatives of functions given as computer programs for their elimination. We review the main characteristics and application of AD and illustrate the methodology on a simple example.
Griewank, Andreas, Walther, Andrea
openaire +2 more sources
St. Petersburg Polytechnical University Journal: Physics and Mathematics, 2023 In the paper, the two main approaches to calculating the Jacobian of the Navier–Stokes equations, namely, the continuum (CA) and discrete (DA) approaches, have been directly compared for the first time. The DA to calculating this Jacobian was implemented
Golubkov Valentin, Garbaruk Andrey
doaj +1 more source
Wide-Angular Tolerance Optical Filter Design and Its Application to Green Pepper Segmentation
Sensors, 2023 The optical filter is critical in many applications requiring wide-angle imaging perception. However, the transmission curve of the typical optical filter will change at an oblique incident angle due to the optical path of the incident light change.
Jun Yu, Shu Zhan, Toru Kurihara
doaj +1 more source
Mixed-language automatic differentiation [PDF]
Optimization Methods and Software, 2018 As Automatic Differentiation (AD) usage is spreading to larger and more sophisticated applications, problems arise for codes that use several programming languages. This work describes the issues involved in interoperability between languages and focuses on the main issue which is parameter passing.
Pascual, Valérie, Hascoët, Laurent
openaire +3 more sources
Selective Path Automatic Differentiation: Beyond Uniform Distribution on Backpropagation Dropout
IEEE Access, 2023 This paper introduces Selective Path Automatic Differentiation (SPAD), a novel approach to reducing memory consumption and mitigating overfitting in gradient-based models for embedded artificial intelligence.
Paul Peseux +3 more
doaj +1 more source
Differentiable Automatic Data Augmentation [PDF]
, 2020 Data augmentation (DA) techniques aim to increase data variability, and thus train deep networks with better generalisation. The pioneering AutoAugment automated the search for optimal DA policies with reinforcement learning. However, AutoAugment is extremely computationally expensive, limiting its wide applicability.
Li, Yonggang +5 more
openaire +4 more sources
CasADi -- A symbolic package for automatic differentiation and optimal control [PDF]
, 2012 We present CasADi, a free, open-source software tool for rapid, yet efficient solution of optimization problems in general and dynamic optimization problems in particular. To the developer of algorithms for numerical optimization and to the advanced user
Andersson, Joel +3 more
core +1 more source
A Modification of Weeks' Method for Numerical Inversion of the Laplace Transform in the Real Case Based on Automatic Differentiation [PDF]
, 2008 Numerical inversion of the Laplace transform on the real axis is an inverse and ill-posed problem. We describe a powerful modification of Weeks' Method, based on automatic differentiation, to be used in the real inversion.
CUOMO, SALVATORE +7 more
core +1 more source
Evolution of perturbations in 3D air quality models
Annals of Geophysics, 2003 The deterministic approach of sensitivity analysis is applied on the solution vector of an Air Quality Model. In particular, the photochemical CAMx code is augmented with derivatives utilising the automatic differentiation software ADIFOR.
I. Ziomas +3 more
doaj +1 more source