DiffSharp is an automatic differentiation (AD) library. AD allows exact and efficient calculation of derivatives, by systematically invoking the chain rule of calculus at the elementary operator level during program execution. AD is different from numerical differentiation, which is prone to... More information
  • 16,784 total downloads
  • last updated 6/12/2020
  • Latest version: 1.0.0
FSharp.Data.Adaptive provides an incremental evaluation system inspired by Adapton, DeltaML and many others for FSharp. The implementation provides incremental datastructures for refs/sets/lists/maps.
Hype is a proof-of-concept deep learning library, where you can perform optimization on compositional machine learning systems of many components, even when such components themselves internally perform optimization. This is enabled by nested automatic differentiation (AD) giving you access to the... More information