"Automatic differentiation"의 두 판 사이의 차이

수학노트
둘러보기로 가기 검색하러 가기
(→‎노트: 새 문단)
 
(→‎메타데이터: 새 문단)
32번째 줄: 32번째 줄:
 
===소스===
 
===소스===
 
  <references />
 
  <references />
 +
 +
== 메타데이터 ==
 +
 +
===위키데이터===
 +
* ID :  [https://www.wikidata.org/wiki/Q787371 Q787371]

2020년 12월 26일 (토) 05:07 판

노트

  • Automatic differentiation (AD) is a way to accurately and efficiently compute derivatives of a function written in computer codes.[1]
  • Automatic differentiation in Swift is a compiler transform implemented as a static analysis.[2]
  • In section 2 , we provide a small review of the algebra behind automatic differentiation.[3]
  • parsing make implementing and using techniques from automatic differentiation easier than ever before (in our biased opinion).[4]
  • Includes support for automatic differentiation of user-provided functions.[4]
  • For a well-written simple introduction to reverse-mode automatic differentiation, see Justin Domke's blog post.[4]
  • Automatic differentiation may be one of the best scientific computing techniques you’ve never heard of.[5]
  • This is specific to so-called forward mode automatic differentiation.[6]
  • Generally speaking, automatic differentiation is the ability for a software library to compute the derivatives of arbitrary numerical code.[7]
  • Our goal was to add automatic differentiation to Bril.[8]
  • Automatic Differentiation is a technique to calculate the derivative for arbitrary computer programs.[8]
  • There are two primary ways of doing automatic differentiation.[8]
  • This is a cool method of doing automatic differentiation, recently popularized by Julia.[8]
  • Automatic Differentiation is the numerical computation of exact values of the derivative of a function at a given argument value.[9]
  • Automatic differentiation can be implemented in various ways.[9]
  • The most widely used operator-overloading code is ADOL-C (Automatic Differentiation by OverLoading in C++) developed by Griewank et al.[9]
  • The code obtained by automatic differentiation, although being accurate, was less efficient than the numerical approach.[9]
  • GradientTape API for automatic differentiation; that is, computing the gradient of a computation with respect to some inputs, usually tf.[10]
  • The autograd package provides automatic differentiation for all operations on Tensors.[11]
  • Therefore, the method of automatic differentiation can be easily coded in programming languages such as FORTRAN and PASCAL.[12]
  • The answer lies in a process known as automatic differentiation.[13]
  • A package that provides an intuitive API for Automatic Differentiation (AD) in Haskell.[14]
  • Automatic differentiation provides a means to calculate the derivatives of a function while evaluating it.[14]
  • Automatic differentiation has been used for at least 40 years and then rediscovered and applied in various forms since.[15]
  • Earlier, we demonstrated how to find the gradient of a multivariable function using the forward mode of automatic differentiation.[15]
  • Introduction to Automatic Differentiation and MATLAB Object-Oriented Programming.[15]
  • Forward mode automatic differentiation is accomplished by augmenting the algebra of real numbers and obtaining a new arithmetic.[16]
  • Automatic Differentiation gives exact answers in constant time.[17]
  • This entire discussion may have given you the impression that Automatic Differentiation is a technique for numeric code only.[17]

소스

  1. ↑ Application of automatic differentiation in TOUGH2
  2. ↑ AutomaticDifferentiation.md at main · tensorflow
  3. ↑ Automatic Differentiation in Quantum Chemistry with Applications to Fully Variational Hartree–Fock
  4. ↑ 4.0 4.1 4.2 JuliaDiff
  5. ↑ Introduction to Automatic Differentiation
  6. ↑ Differentiating the discrete: Automatic Differentiation meets Integer Optimization
  7. ↑ Automatic differentiation — PennyLane
  8. ↑ 8.0 8.1 8.2 8.3 Automatic Differentiation in Bril
  9. ↑ 9.0 9.1 9.2 9.3 Automatic differentiation tools in the dynamic simulation of chemical engineering processes
  10. ↑ Introduction to Gradients and Automatic Differentiation
  11. ↑ Autograd: Automatic Differentiation — PyTorch Tutorials 1.7.1 documentation
  12. ↑ Automatic Differentiation and Applications
  13. ↑ Automatic Differentiation, Explained
  14. ↑ 14.0 14.1 ad: Automatic Differentiation
  15. ↑ 15.0 15.1 15.2 AMS :: Feature Column :: How to Differentiate with a Computer
  16. ↑ Automatic differentiation
  17. ↑ 17.0 17.1 Automatic Differentiation Step by Step

메타데이터

위키데이터

원본 주소 "https://wiki.mathnt.net/index.php?title=Automatic_differentiation&oldid=47365"