Blog

The OCaml Planet RSS

Articles and videos contributed by both experts, companies and passionate developers from the OCaml community. From in-depth technical articles, project highlights, community news, or insights into Open Source projects, the OCaml Planet RSS feed aggregator has something for everyone.

Type

All Article Video

Source

Tarides 227 Anil Madhavapeddy's Blog 220 Watch OCaml 204 Caml Weekly News 188 OCamlPro 170 Marc Elvers 147 Jane Street Tech Blog 124 MirageOS 79 Coq 78 Frama-C 76 Robur Cooperative 70 Caml INRIA 53 Jon Ludlam's Blog at recoil.org 53 Daniel Bünzli 42 David Allsopp's Blog 31

Keyword

opam 281 compiler 200 mirageos 195 dune 185 functional programming 162 ppx 132 unikernel 132 async 125 multicore 123 functor 115 eio 114 parser 114 odoc 112 domain 104 effect 103 merlin 103 lwt 102 monad 99 js_of_ocaml 89 concurrency 88 gradient 0

Year

2026 312 2025 425 2024 306 2023 242 2022 149 2021 196 2020 141 2019 117 2018 110 2017 99 2016 99 2015 105 2014 137 2013 98 2012 60 2011 52 2010 72 2009 35 2008 19 2007 9 2006 3 2005 4 2004 4 2003 2 2002 2

Author

Anil Madhavapeddy 234 Tarides 226 Unknown 213 Caml Weekly News 181 Mark Elvers 147 Jane Street Tech Blog 112 Coq 78 Frama-C 74 Jane Street 70 Robur Cooperative 70 Jon Ludlam 54 Caml INRIA 53 Daniel Bünzli 42 Bozhidar Batsov 28 Mathématiques et informatique - Collège de France 28

Want your Blog Posts or Videos to Show Here?

To contribute a blog post, or add your RSS feed, check out the Contributing Guide on GitHub.

Add your RSS feed!
Filtering by: Keyword: gradient (remove) Clear all
Machine Learning in OxCaml

The inspiration for this post came from Dave’s Garage YouTube Channel. It featured dbrll/ATTN-11, which used machine learning on a PDP-11 to reverse a sequence of numbers. I’m not (quite) old enough to remember the PDP-11, but the idea of a minimal machine learning example was intriguing, particularly as an aid to understanding.

backward d_model digit_acc ex_acc gradient layernorm loss model row training

07 May 2026

Marc Elvers

Read Article
L2 Regularization and Batch Norm

This blog post is about an interesting detail about machine learningthat I came across as a researcher at Jane Street - that of the interaction between L2 re...

batch convolutional decay gradient norm penalty rate regularization weight weights

29 Jan 2019

Jane Street Tech Blog

Read Article
Does batch size matter?

This post is aimed at readers who are already familiar withstochastic gradient descent(SGD) and terms like “batch size”. For an introduction to theseideas, ...

batch gradient mandt matter posterior sde sgd size smith temperature

31 Oct 2017

Jane Street Tech Blog

Read Article