awesome-haskell-deep-learning
github.com/austinvhuang/awesome-haskell-deep-learning ↗In the tradition of "awesome" (curated) lists, this is a list of references and code for doing deep learning in Haskell.
Use this list with your AI agent
Add the Context Awesome MCP server to Claude, Cursor, or any MCP client, then ask:
"Show me packages under active development resources from awesome-haskell-deep-learning"
Installation instructions →What's inside
Talks
- A Functional Reboot for Deep Learning (BOB 2019 Talk)
- Berlin Functional Programming Group: Hasktorch
- Keynote: Automatic Diferentiation for Dummies
- MuniHac 2020: Austin Huang - Hasktorch: Differentiable Functional Programming in Haskell
Hasktorch: Differentiable Functional Programming in Haskell
- NPFL Numerical Programming in Functional Languages (ICFP Session) 2018 Playlist
- The Simple Essence of Automatic Differentiation
Articles
- A Purely Functional Typed Approach to Trainable Models
- Backpack for deep learning
- Backprop as Functor: A compositional perspective on supervised learning
- Backpropogation is Just Steepest Descent with Automatic Differentiation
- Computing symbolic gradient vectors with plain Haskell
- DeepDarkFantasy: A Programming Language for Deep Learning
Haskell Packages
- arrayfire-haskellPackages Under Active Development
High-level Haskell bindings to the
- backprop-hmatrixPackages Under Active Development
Automatic heterogeneous back-propagation that can be used either implicitly (in the style of the ad library) or using explicit graphs built in monadic style. |
- convolutedLegacy Packages
Dependently typed convolutional neural networks in pure Haskell. Uses the repa library for high-performance arrays, with a static wrapper that ensures networks are valid at compile-time. |
- deeplearning-hsLegacy Packages
- dexPackages Under Active Development
a research language for typed, functional array processing.
- diffhaskPackages Under Active Development
DSL for forward and reverse mode automatic differentiation via a version of operator overloading. Port of DiffSharp to Haskell; currently a work in progress. |
Showing a sample of 49 resources. View the full list on GitHub →