Skip to content

Experimental automatic differentiation library for learning purposes.

License

Notifications You must be signed in to change notification settings

doorisajar/ToyAD.jl

Repository files navigation

ToyAD.jl

lifecycle build codecov.io

Prototype implementation of automatic differentiation for learning purposes while reading Evaluating Derivatives: Principles & Techniques of Algorithmic Differentiation (2nd Edition). Starting with forward mode, and (if time permits) moving on to reverse mode.

Currently working functionality is shown in the unit tests:

  • Forward mode differentiation for scalar-valued functions utilizing a subset of operators
  • Gradients for vector-valued functions
  • Row-wise and columnar Jacobian calculations for vector to vector functions

Built without LLM assistance; references linked where appropriate.

About

Experimental automatic differentiation library for learning purposes.

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Contributors 3

  •  
  •  
  •  

Languages