Displaying 1 to 1 from 1 results

XDiff.jl - eXpression differentiation in Julia

  •    Julia

This package is unique in that it can differentiate vector-valued expressions in Einstein notation. However, if you only need gradients of scalar-valued functions (which is typicial in machine learning), please use XGrad.jl instead. XGrad.jl is re-thought and stabilized version of this package, adding many useful featues in place of (not frequently used) derivatives of vector-valued functions. If nevertheless you want to continue using XDiff.jl, please pin Espresso.jl to version v3.0.0, which is the last supporting Einstein notation. XDiff.jl is an expression differentiation package, supporting fully symbolic approach to finding tensor derivatives. Unlike automatic differentiation packages, XDiff.jl can output not only ready-to-use derivative functions, but also their symbolic expressions suitable for further optimization and code generation.