backprop
Heterogeneous automatic differentiation ("backpropagation") in Haskell (by mstksg)
grenade
Deep Learning in Haskell (by HuwCampbell)
backprop | grenade | |
---|---|---|
2 | 5 | |
177 | 1,439 | |
- | - | |
3.8 | 5.6 | |
7 months ago | 5 months ago | |
Haskell | Haskell | |
BSD 3-clause "New" or "Revised" License | BSD 2-clause "Simplified" License |
The number of mentions indicates the total number of mentions that we've tracked plus the number of user suggested alternatives.
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
backprop
Posts with mentions or reviews of backprop.
We have used some of these posts to build our list of alternatives
and similar projects. The last one was on 2023-01-17.
grenade
Posts with mentions or reviews of grenade.
We have used some of these posts to build our list of alternatives
and similar projects. The last one was on 2023-01-23.
-
Haskell deep learning tutorials [Blog]
Grenade is fun, but it does not support CUDA, so it will limit you. I would say that this was a great experiment that has influenced the Hasktorch library in different ways (let me know if I am wrong).
- Dhall: A Gateway Drug to Haskell
-
Haskell for Artificial Intelligence?
FWIW there's an interesting library called grenade which offers nice types for constructing neural nets. I haven't used it, and this is not my areas of expertise, but it looks cool!
-
Rank 3 Stencils for "Efficient Parallel Stencil Convolution in Haskell" (Repa)
When I wrote grenade I used the im2col trick to turn convolutions into a single matrix multiplication, which could then be done in hmatrix.
- What are some ways I could tickle my (beginner) haskell-brain with something *useful*?
What are some alternatives?
When comparing backprop and grenade you can also consider the following projects:
forecast-io - A Haskell library for working with forecast.io data.
hasktorch - Tensors and neural networks in Haskell
swagger2 - Swagger 2.0 data model.
liblinear-enumerator - Haskell bindings to liblinear
inquire
simple-neural-networks - Simple parallel neural networks implementation in pure Haskell
json - Haskell JSON library
CV - Haskell wrappers and utilities for OpenCV machine vision library
listenbrainz-client - A client to the ListenBrainz project
nn - A tiny neural network ðŸ§
clock-extras
hnn - haskell neural network library