A gentle reminder that TMLR is a great journal that allows you to submit your papers when they are ready rather than rushing to meet conference deadlines. The review process is fast, there are no artificial acceptance rates, and you have more space to present your ideas in the

Interested in using reinforcement learning to train LLMs for problems where there’s no room for error? Do you want to build massive data pipelines to transform how we interact with scientific knowledge? We're hiring for multiple roles at Reliant: https://t.co/hzTqp6Z6To

I have fully-funded PhD positions (3.5 yrs) for troublemakers in #ML #AI who want to design the next gen of #probabilistic #models and #programs that are provably #reliable and #efficient Join @InfAtEd @EdinburghUni Email me! ✉️ Please share! 🔁 Apply 👉 https://t.co/ReIiIshYy7

April 12-14 we are organizing the International Symposium on Intelligent Data Analysis in Louvain-la-Neuve, with 4 invited speakers, 38 paper presentations, 19 presenters in the PhD forum, and a social program. Consider registering! More information on https://t.co/NvRIvAsL0z.

Thanks @SGRNijssen and @pschaus for the collaboration. It is a great pleasure to work with you during these years of my PhD.

@gael_aglin presented "Learning Optimal Decision Trees under Memory Constraints" today at @ECMLPKDD 2022, joined work with @pschaus, in which we address the problem that the DL8.5 algorithm can be too memory consuming. Check the paper here: https://t.co/TZRrGle5Su

Here is what Machine Learning tutorials told you to do: 1. Start by transforming your dataset 2. Then split it (train, validation, and test sets) 3. Finally, build your model Please, unlearn this process. There's a problem with it: 1 of 11

First Principles of Computer Vision, Columbia University Really nice lectures on the physical and mathematical foundations of computer vision. 140 videos that you can watch at your pace. Slides are also provided to follow along. https://t.co/GqPlV2SzSU

Congratulations to Gaël and Harold! In this work we address important remaining weaknesses of DL8.5, our state-of-the-art algorithm for finding optimal decision trees: its use of exponential amounts of memory & tendency to get stuck in one part of the search. Papers online soon!

Cotonou ! Il paraît que son marché gigantesque (juste au-dessus d’un des ponts) voit passer toute l’Afrique de l’Ouest ! 🇧🇯 Cotonou, #Benin, with some cute ☁ cover. The city looks like two halves growing towards each other, maybe even giving each other a fist bump 🤜🤛

La magie du football 😂

Okwugbé, first ASR initiative for Fon and Igbo is now available. Such a nice work with @ChrisEmezue. We open-source codes and data to encourage similar works on low-resourced African Languages 🤗. Fon: https://t.co/vdtyd3NQkR Igbo: https://t.co/TWtrjxZQTq

We have open PhD positions in the groups of @TiasGuns, @jessejdavis1, Angelika Kimmig, @HendrikBlockeel , @lucderaedt . Apply now (positions will close when a candidate is retained): https://t.co/R3lF4qEt9I #artificialintelligence #machinelearning #reasoning #hiring

This work builds on an earlier paper, presented at #AAAI2020. We have improved the performance of our implementation and made it easier to use our algorithm for solving a wide variety of decision tree learning problems. @gael_aglin will be happy to tell you all about it!

Five tenure-track academic positions at @UCLouvain_be in Computer Science applied to life sciences, Safety critical embedded systems, Mathematics for AI, Mathematical optimisation and Automation and process control. Application deadline: mid November 2020 https://t.co/2qSxlPi8AC

I am very excited to release the recordings of my Machine Learning lectures! You can watch the first lecture here: https://t.co/vOKSPHiZbg. If you want to follow the course, readings, lecture notes, and assignments will be made available at https://t.co/bkLPVdEqAT.

Unsupervised Translation of Programming Languages. Feed a model with Python, C++, and Java source code from GitHub, and it automatically learns to translate between the 3 languages in a fully unsupervised way. https://t.co/FpUL886KS7 with @MaLachaux @b_roziere @LowikChanussot

3) The paper "PyDL8.5: a Library for Learning Optimal Decision Trees", by @gael_aglin, @SGRNijssen and @pschaus was accepted in the demo track of the @IJCAIconf !

Just found this gem: https://t.co/nt5UGtqoV6 Algorithms from Bishop's legendary "Pattern Recognition and Machine Learning" book implemented in Python. And not just that, but the code is extremely clean, beautiful, and well-documented.