Yota.jl is a package for reverse-mode automatic differentiation in Julia. The main features are:
- optimized for large inputs and conventional deep learning
- tracer-based with a hackable computational graph (tape)
- supports ChainRules API
| Name | Name | Last commit date | ||
|---|---|---|---|---|
Yota.jl is a package for reverse-mode automatic differentiation in Julia. The main features are: