TLDR:
Participated in the @AI4ClimateCoop competition organised by @Mila_Quebec. Had fun with the team (@phillipjw, Claudia Wieners, @rloftin4400, @erman_ai) and managed to win 2 out of the 3 tracks.
Designing AI-based support tools that extend human capabilities is a promising direction that is also pushed by the #HybridIntelligenceCentre that part of our team is affiliated too. Now let's see what can be done with the insights gained during this competition.
Got interviewed by @RadioWeetlust (in Dutch) this morning about my work. They are bringing science to the public by interviewing a scientist every day as part of Leiden being the European city of science in 2022 @ESOF_eu@leiden2022. Cool project and thanks for having me!
I like the idea of creating a “CERN for AI” in Europe, a lighthouse that attracts AI researchers. It would be great to create an AI powerhouse without a commercial motive.
Our @ada_research professor @HolgerHoos at the “AI made in europe” panel at #IJCAI2022. Great discussion on how to push and position European AI research.
We designed a central website for reinforcement learning research happening in the Belgium-Netherlands region: https://t.co/uFa2VWlY5F. Please visit the website to indicate if you want to be listed, and to potentially sign up for the mailing list!
@willem_ropke The day that I found out they encrypt your local library due to a half-baked GDPR excuse (https://t.co/Igl4jC4BbC), I lost faith and switched to Zotero.
The latest version of Mendeley prevents you from getting all of your data out of the app. We’ve added instructions for transferring your full library to Zotero — which will always remain open — while you still can. https://t.co/P8Uycgk9nS
(1/n)
How to start a deep learning project?
We use a remarkably streamlined step-by-step process to set up deep learning projects. At the same time, people who are new to deep learning tend to always make the same (avoidable) mistakes.
Check out the thread below! 🧵
New paper (open access!), with Gilles Ottervanger and Mitra Baratchi, on #AutoML for early time series classification: https://t.co/HzdXy6FCGv @mitrabaratchi@ada_research@LIACS