ReverseDiff is a fast and compile-able tape-based reverse mode automatic differentiation (AD) that implements methods to take gradients, Jacobians, Hessians, and higher-order derivatives of native Julia functions (or any callable object, really). While performance can vary depending on the functions you evaluate, the algorithms implemented by ReverseDiff generally outperform non-AD algorithms in both speed and accuracy.
Features
- Supports a large subset of the Julia language, including loops, recursion, and control flow
- User-friendly API for reusing and compiling tapes
- Compatible with ForwardDiff, enabling mixed-mode AD
- Built-in definitions leverage the benefits of ForwardDiff's Dual numbers (e.g. SIMD, zero-overhead arithmetic)
- Familiar differentiation API for ForwardDiff users
- Non-allocating linear algebra optimizations
- Suitable as an execution backend for graphical machine learning libraries
Categories
Data VisualizationLicense
MIT LicenseFollow ReverseDiff
You Might Also Like
Monitor your whole IT Infrastructure
Caters to tech staff, system Administrators, and companies of any size, from small and medium sized businesses to enterprises that need their IT network to be reliable and easy to monitor in real-time. Equipped with an easy-to-use, intuitive interface with a cutting-edge monitoring engine. PRTG optimizes connections and workloads as well as reducing operational costs by avoiding outages while saving time and controlling service level agreements (SLAs).
Rate This Project
Login To Rate This Project
User Reviews
Be the first to post a review of ReverseDiff!