Results 1 to 10 of about 87,618 (263)
Automatic Differentiation in ROOT [PDF]
EPJ Web of Conferences, 2020 In mathematics and computer algebra, automatic differentiation (AD) is a set of techniques to evaluate the derivative of a function specified by a computer program.
Vassilev Vassil +2 more
doaj +3 more sources
Automatic Differentiation for Inverse Problems in X-ray Imaging and Microscopy [PDF]
Life, 2023 Computational techniques allow breaking the limits of traditional imaging methods, such as time restrictions, resolution, and optics flaws. While simple computational methods can be enough for highly controlled microscope setups or just for previews, an ...
Francesco Guzzi +4 more
doaj +2 more sources
MapsTorch: automatic differentiation for X-ray fluorescence data analysis [PDF]
Journal of Synchrotron RadiationX-ray fluorescence (XRF) is a popular spectroscopy technique for elemental analysis. Spectrum fitting and parameter tuning are at the core of XRF analysis and are conventionally manually intensive, especially for synchrotron experiments involving large ...
Xiangyu Yin +5 more
doaj +2 more sources
The simple essence of automatic differentiation [PDF]
Proceedings of the ACM on Programming Languages, 2018 Automatic differentiation (AD) in reverse mode (RAD) is a central component of deep learning and other uses of large-scale optimization. Commonly used RAD algorithms such as backpropagation, however, are complex and stateful, hindering deep understanding, improvement, and parallel execution.
Conal Elliott
exaly +3 more sources
Automatic differentiation in PCF [PDF]
Proceedings of the ACM on Programming Languages, 2021 We study the correctness of automatic differentiation (AD) in the context of a higher-order, Turing-complete language (PCF with real numbers), both in forward and reverse mode. Our main result is that, under mild hypotheses on the primitive functions included in the language, AD is almost everywhere correct, that is, it computes the ...
Damiano Mazza, Michele Pagani
openaire +4 more sources
A taxonomy of automatic differentiation pitfalls
Wiley Interdisciplinary Reviews: Data Mining and Knowledge DiscoveryAbstractAutomatic differentiation is a popular technique for computing derivatives of computer programs. While automatic differentiation has been successfully used in countless engineering, science, and machine learning applications, it can sometimes nevertheless produce surprising results.
Jan Hückelheim +2 more
exaly +3 more sources
Automatic Differentiation in Prolog
Theory and Practice of Logic Programming, 2023 AbstractAutomatic differentiation (AD) is a range of algorithms to compute the numeric value of a function’s (partial) derivative, where the function is typically given as a computer program or abstract syntax tree. AD has become immensely popular as part of many learning algorithms, notably for neural networks. This paper uses Prolog to systematically
Schrijvers, Tom +2 more
openaire +5 more sources
Federated Automatic Differentiation
J. Mach. Learn. Res., 2023 39 pages, 13 figures. To appear in JMLR 25 (2024)
Keith Rush +2 more
openaire +3 more sources
Application of Generalized (Hyper-) Dual Numbers in Equation of State Modeling
Frontiers in Chemical Engineering, 2021 The calculation of derivatives is ubiquitous in science and engineering. In thermodynamics, in particular, state properties can be expressed as derivatives of thermodynamic potentials. The manual differentiation of complex models can be tedious and error-
Philipp Rehner, Gernot Bauer
doaj +1 more source
Application of seeding and automatic differentiation in a large scale ocean circulation model [PDF]
Modeling, Identification and Control, 2005 Computation of the Jacobian in a 3-dimensional general ocean circulation model is considered in this paper. The Jacobian matrix considered in this paper is square, large and sparse.
Frode Martinsen, Dag Slagstad
doaj +1 more source