Re:L2 Regularization and Batch Norm
by phonebucket on Tuesday July 23, 2019 @04:40AM
(#20505311)
Jane Street is noted for its use of OCaml, so it's interesting to see that their researchers do indeed use Python (judging from the code in that post, at least).
[ Parent
| on HN ]
They've also used OCaml for deep learning: https://blog.janestreet.com/deep-learning-experiments-in-oca...
Although it seems to be an OCaml binding into TF, rather than a native implementation.
Re:L2 Regularization and Batch Norm
by stochastic_monk on Wednesday July 24, 2019 @08:22PM
(#20521495)
There’s a similar tch-rs project wrapping libtorch, and in general, deeclaring neural networks is particularly intuitive in functional languages.
There is a project that aims to bring NN/ML/DL/RL (along with other scientific computations) in the OCaml world - Owl[1]. They also have a list[2] of the potentially interesting ideas for new contributors to take.