Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
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.
https://github.com/austinvhuang/awesome-haskell-deep-learning
- Type-driven Neural Programming by Example
- Dex: array programming with typed indices
- Not-o-matic Differentiation
- Hasktorch v0.0.1
- The Simple Essence of Automatic Differentiation
- A Purely Functional Typed Approach to Trainable Models
- Introducing the backprop library
- Backprop as Functor: A compositional perspective on supervised learning
- Haskell and AI (multi-part series covering Tensorflow)
- Backpack for deep learning
- DeepDarkFantasy: A Programming Language for Deep Learning
- Deep Learning, from a Programming Language Perspective
- Computing symbolic gradient vectors with plain Haskell
- Practical Dependent Types in Haskell (Part 2): Existential Neural Networks and Types at Runtime
- Practical Dependent Types in Haskell (Part 1): Type-Safe Neural Networks
- Reverse-Mode Automatic Differentiation in Haskell Using the Accelerate Library (CS240h project)
- Neural Networks, Types, and Functional Programming
- Get a Brain
- Backpropogation is Just Steepest Descent with Automatic Differentiation
- PyTorch Developer Day 2020: Torch for R & Hasktorch: Bringing Torch to New Programming Languages
- Berlin Functional Programming Group: Hasktorch
- MuniHac 2020: Austin Huang - Hasktorch: Differentiable Functional Programming in Haskell
- A Functional Reboot for Deep Learning (BOB 2019 Talk)
- Keynote: Automatic Diferentiation for Dummies
- NPFL Numerical Programming in Functional Languages (ICFP Session) 2018 Playlist
- The Simple Essence of Automatic Differentiation
- backprop - 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. | [Justin Le](https://github.com/mstksg)
- arrayfire-haskell - High-level Haskell bindings to the [ArrayFire](https://github.com/arrayfire/arrayfire) General-purpose GPU library. | [David Johnson](https://github.com/dmjio)
- backprop-hmatrix - 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. | [Justin Le](https://github.com/mstksg)
- dex - a research language for typed, functional array processing.
- diffhask - DSL for forward and reverse mode automatic differentiation via a version of operator overloading. Port of DiffSharp to Haskell; currently a work in progress. | [Tim Pierson](https://github.com/o1lo01ol1o)
- funn - This is an experimental library exploring a combinator approach for building and training neural networks in haskell. | [Neil Shepperd](https://github.com/nshepperd)
- grenade - Grenade is a composable, dependently typed, practical, and fast recurrent neural network library for concise and precise specifications of complex networks in Haskell. | [Huw Campbell](https://github.com/HuwCampbell)
- gym-http-api - source library, includes a Haskell client by [Sam Stites](https://github.com/stites)
- hasktorch
- hasktorch-yolo
- hnn - A neural network library implemented purely in Haskell, relying on the hmatrix library. | [Alp Mestan](https://github.com/alpmestan)
- rc - Reservoir computing library. | [Bogdan Penkovsky](https://github.com/masterdezign)
- synthesis - Implementation for [Typed Neuro-Symbolic Program Synthesis for the Typed Lambda Calculus](https://arxiv.org/abs/2008.12613)
- tensor-safe - A framework to define valid deep neural network models and export them to specific languages | [Leonardo Pineyro](https://github.com/leopiney)
- tensorflow - The tensorflow-haskell package provides Haskell bindings to TensorFlow. | [Judah Jacobson](https://github.com/judah) and [Greg Steuk](https://github.com/blackgnezdo)
- TypedFlow - TypedFlow is a typed, higher-order frontend to TensorFlow and a high-level library for deep-learning. Generates python. | [Jean-Philippe Bernardy](https://github.com/jyp)
- convoluted - 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. | [Jonas Carpay](https://github.com/jonascarpay)
- deeplearning-hs
- dnngraph
- lambdanet
- neural - The goal of neural is to provide a modular and flexible neural network library written in native Haskell. | [Lars Brünjes](https://github.com/brunjlar)
- Chris Olah's blog
- dataHaskell site
- idontgetoutmuch blog
- Justin Le's blog
- Monday Morning Haskell
Programming Languages