(yet) Neural Ordinary Differential Equations (NODEs) and Deep Implicit Layers

< 목차 >

• Motivation
• Preliminaries
  • Euler Method: A First-order Numerical Procedure For Solving Ordinary Differential Equations (ODEs)
• Neural Ordinary Differential Equations (NODEs)
  • tmp
• References

수학적인 직관이 있어 paper를 읽는데 어려움이 업다면 Neural Ordinary Differential Equations를 바로 봐도 좋지만, 그게 아니라면 NIPS에서 저자들의 presentation video와 KAIST의 Edward Choi 교수님의 AI504 lecture video를 먼저 보고 paper를 읽기를 추천한다.

Motivation

Preliminaries

Euler Method: A First-order Numerical Procedure For Solving Ordinary Differential Equations (ODEs)

Fig. Source from Wiki

Fig.

Neural Ordinary Differential Equations (NODEs)

tmp

Fig.

Fig.

Fig.

Fig.

Fig.

Fig.

Fig.

Fig.

Fig.

Fig.

Fig.

Fig.

References

• Preliminaries
  • Euler method
  • Direction Fields and Numerical Methods
  • Euler’s Method for Solving Ordinary Differential Equations
• Papers
  • Neural Ordinary Differential Equations
• Videos
  • Programming for AI (AI504, Fall 2020), Class 14: Neural Ordinary Differential Equations from Edawrd Choi
    • slide
  • Neural Ordinary Differential Equations - Best Paper Awards NeurIPS
  • NIPS 2020 tutorial. Deep Implicit Layers
    • youtube video
  • Neural Ordinary Differential Equations from Yannic Kilcher
  • Neural Ordinary Differential Equations from Andriy Drozdyuk
  • Neural ODEs (NODEs) (Physics Informed Machine Learning) from Steve Brunton
• codes
  • PyTorch Implementation of Differentiable SDE Solvers