inf-backprop: Automatic differentiation and backpropagation.

[ bsd3, library, mathematics ] [ Propose Tags ] [ Report a vulnerability ]

Automatic differentiation library with efficient reverse-mode backpropagation for Haskell.

This package provides a general-purpose automatic differentiation system designed for building strongly typed deep learning frameworks. It offers:

  • Reverse-mode automatic differentiation (backpropagation)

  • Support for higher-order derivatives

  • Type-safe gradient computation

  • Integration with numhask

  • Flexible representations including profunctor and Van Laarhoven encodings

The library emphasizes composability and type safety, making it suitable for research, prototyping neural networks, and implementing custom differentiable algorithms.

See the tutorial for detailed examples and usage patterns.

Similar Projects:

  • ad - Comprehensive automatic differentiation library supporting forward and reverse modes

  • backprop - Heterogeneous automatic differentiation with emphasis on ease of use

Downloads

Maintainer's Corner

Package maintainers

For package maintainers and hackage trustees

Candidates

Versions [RSS] 0.1.0.0, 0.1.0.1, 0.1.0.2, 0.1.1.0, 0.2.0.0
Change log CHANGELOG.md
Dependencies base (>=4.7 && <5), combinatorial (<0.2), comonad (<5.1), composition (<1.1), data-fix (<0.4), deepseq (<1.6), extra (<1.9), finite-typelits (<0.3), fixed-vector (<2.1), ghc-prim (<0.13), hashable (<1.6), indexed-list-literals (<0.3), isomorphism-class (<0.4), lens (<5.4), numhask (<0.14), optics (<0.5), primitive (<0.10), profunctors (<5.7), safe (<0.4), simple-expr (<0.3), Stream (<0.5), text (<2.2), transformers (<0.7), unordered-containers (<0.3), vector (<0.14), vector-sized (<1.7) [details]
License BSD-3-Clause
Copyright 2023-2025 Alexey Tochin
Author Alexey Tochin
Maintainer Alexey.Tochin@gmail.com
Category Mathematics
Uploaded by AlexeyTochin at 2025-11-19T23:22:02Z
Distributions LTSHaskell:0.1.1.0, NixOS:0.1.1.0, Stackage:0.1.1.0
Downloads 360 total (16 in the last 30 days)
Rating 2.0 (votes: 1) [estimated by Bayesian average]
Your Rating
  • λ
  • λ
  • λ
Status Docs uploaded by user
Build status unknown [no reports yet]