Great talk by @ylecun yesterday, at the scientific symposium for the opening of the @ELLISInst_Tue! I took the liberty of summarizing one of his main take-home messages...
What is an interpretable model? This term, appearing in many regulatory frameworks on AI, lacks a commonly accepted definition.
In a paper to be presented at #COLT2024 this week, we address this problem from a learning-theoretic angle.
arxiv.org/abs/2406.10529
I will be recruiting at least one PhD student via the ELLIS PhD program this year. Go to ellis.eu/phd-postdoc for info and deadline. If you want to work with me, flag my name in the web application form and refer to my work in your cover letter.
At LAILA laila.di.unimi.it/ in Milan we are looking for postdocs eager to work on online learning, multi-armed bandits and RL, active learning, and multi-agent learning. Contact me if you are interested!
Congratulations @YishayMansour for being such an amazing scientist! And many thanks to Avrim Blum and Lee Cohen for organizing #YishayFest at @TTIC_Connect
I was recently asked to review
"Geo-Visual Analysis of Rural Banditry Prevalence in Nigeria: A Panacea to Sustainable Food Supply to Urban Centers"
I eventually declined, yet rural bandits sounds like a legit ICML keyword...
Memorable day at Quirinale to deliver to the President of the Italian Republic the joint statements of the Science7 group (representatives of the G7 Academies of Science). The statements included a document on the challenges brought by AI. #G7Italy
What are the G7 Science Academies recommendations to policymakers on hot global issues such as health, social inequalities, and nuclear arms control? See lincei.it/en/g7-academies-me… for the full list, including the joint statement on AI and Society.
#G7Italy
“With the right regulatory environment, combined with the right ambition and some of the world’s top AI talent, the EU would have a real chance of leading the next generation of tech innovation,” write Mark Zuckerberg and Daniel Ek in a guest essay econ.st/4dJei1u