[Haskell-cafe] Machine Learning Library in Haskell

[Heet Sankesara]

Hello community,
Myself Heet sankesara. I am a machine learning practitioner. I've been
doing it for a year. I recently learned Haskell to implement Markov Logic
Networks. I found the language intuitive. It is far easier to express logic
and formulas in Haskell as compared to languages like Python or R.  So I
decided to do some data science using it but I couldn't because there is no
library like Sklearn in Python. The few libraries I found are mostly
disoriented and undermanaged.
I want to work on machine learning library which can be used easily and
efficiently by machine learning practitioners. It would be helpful for
everyone to have a dedicated machine learning library. For a practitioner,
it would be easier to tweak and test the model and try different algorithms
quickly. For the community, the dedicated library leads the developers to
focus on it and improve it which would result in a more efficient and
flexible library.
The list of algorithms I am planning to implement are as follows:
1. Linear and Logistic Regression
2. Ridge Regression
3. Perceptron
4. SVM classifier and regressor (Both Linear and Non-Linear)
5. Stochastic Gradient Descent
6. K-means clustering and  KNN classifier
7. Naive Bayes
8. Decision trees
9. Random Forest
10. Gradient boosting
11. Ada boost
12. Voting classifier
13. Neural Network
14. Gradient Descent, Momentum, Nesterov accelerated gradient
15. Adaptive Moment Estimation (Adam optimizer)
Please consider this idea for GSoC this year. I am be happy to talk about
the idea and possible algorithms that can be implemented in the upcoming
summer.
With regards,
Heet Sankesara
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://mail.haskell.org/pipermail/haskell-cafe/attachments/20190311/49bf028f/attachment.html>