Was literally unbelievable to see. And was unfortunately not an isolated case. I do believe in the process, am ok with noise in reviews - but not with this.

I am pleased to announce that as of today I am an Associate Professor at the University of Pisa Università di Pisa. I want to thank all the collaborators and researchers who have crossed my path in this fantastic ride so far. The journey has only just begun. ❤️

I am hiring 3 postdocs at #KAUST to develop an Artificial Scientist for discovering novel chemical materials for carbon capture. Join this project with Francesco Faccio @ ICLR2025 🇸🇬 at the intersection of RL and Material Science. Learn more and apply: faccio.ai/postdoctoral-p…

MIT's "Mathematics for Computer Science". A 1048 page available for Free.

A really nice 628 page textbook for Mathematics from Carnegie Mellon University. I like the Author's description "The goal of this book is to help the reader make the transition from being a consumer of mathematics to a producer of it. This is what is meant by ‘pure’

And the 2024 Nobel Prize in Physics does not go to physics...

Maybe in some time we’ll be happy for this nobel in physics to some relevant machine learning godfathers. But today it just feels cringe.

The #NobelPrizeinPhysics2024 for Hopfield & Hinton rewards plagiarism and incorrect attribution in computer science. It's mostly about Amari's "Hopfield network" and the "Boltzmann Machine." 1. The Lenz-Ising recurrent architecture with neuron-like elements was published in

Intelligence at the Edge of Chaos arxiv.org/abs/2410.02536 They study the behavior of LLMs trained on 1D cellular automata, and examine their behavior when the CAs are near “edge of chaos” regions. The paper’s ideas still needs to be further refined IMO, but a fun paper to read!

If you're interested in AI, machine learning, data science, and black box models, you might enjoy my chat with Stanford University statistician Emmanuel Candès.

Learning and memory in non neural cells (such as kidney cells)

every function is differentiable if you’re not a coward

double-blind peer review

François Chollet Besides Keras, your 60 page writeup on the measure of intelligence was great. It proposed the right and pragmatic perspective to think about generalization. Best of luck in your new journey! arxiv.org/abs/1911.01547

#LOT very interesting interactive lecture by Claudio Gallicchio "Reservoir Computing Methods for Time Series Classification" Andrea Cossu Vincenzo Lomonaco Stefano Melacci

*Deep Learning is Not So Mysterious or Different* by Andrew Gordon Wilson Fantastic paper showing that many interesting phenomena (e.g., double descent) can be understood in the frameworks of PAC-Bayes and "soft inductive biases". Great visuals! 😍 arxiv.org/abs/2503.02113

🚨The 3rd workshop on #DeepLearning meets #Neuromorphic #Hardware at #ECMLPKDD2025 is still accepting contributions! 🚨 🗓 Sept. 15-19, 2025 🇵🇹 Porto, Portugal ,ℹ lnkd.in/dssnPsaB 🗓️ Submission deadline: June 14 2025 #DeepLearning #NeuromorphicComputing #Reservoir