Aurélien Geron

My new book just came out! 🎉😊 Kindle & e-book available now, print within 1–2 weeks. You can get it at: homl.info (you'll also find free online content there) Play with the notebooks at: github.com/ageron/handson… Hope you'll find it useful!

@baizhanbaibolat @OReillyMedia Thanks Baizhan! It's so hard to keep up, but also a lot of fun. 😄 I recently published a new edition using PyTorch: see homl.info

this book opened my eyes. but the ml landscape has shifted. the world needs a 4th edition, gotta keep the heritage alive. let's make it happen! @aureliengeron @OReillyMedia #DataScience #DeepLearning

@HanchungLee Ctrl-C = interrupt Ctrl-D = exit Comes from Unix/POSIX terminal systems, and works in many shells: Bash, Zsh, Python, Node.js, Ruby, PHP, Go, PostgreSQL, MySQL / MariaDB, SQLite, Docker, ssh, Redis, etc. I like it: I can interrupt a program without closing the shell by mistake.

til antigravity cli uses a different hotkey to quit vs claude code, codex, and gemini cli... why?!?!?!?

This is INSANE: Trump’s DOJ says the government is now “FOREVER BARRED” from pursuing tax claims against Trump or his family as part of the “settlement.” The one-page document, signed by Deputy AG Todd Blanche, also blocks claims tied to pending tax returns. The most corrupt president in American history by far.

@pique90s You can run everything locally using Jupyter if you don't want to use Colab: see the instructions at github.com/ageron/handson… Most notebooks will download datasets, but this only happens once. Once you have all the code, libraries and datasets, everything should be fully local. 👍

@aureliengeron I have a love and hate relationship with this book. I am forced to go on GitHub while reading the book but I do not want to be connected to the internet while reading the book.

My new book just came out! 🎉😊 Kindle & e-book available now, print within 1–2 weeks. You can get it at: homl.info (you'll also find free online content there) Play with the notebooks at: github.com/ageron/handson… Hope you'll find it useful!

@skenzyme @OutSomebod70162 @nattyover Glad you find me charming. 😅 A 1 followed by 44 zeros is a large number. The question is: is it large enough? Well, all dog breeds evolved from wolves in less than 30,000 years. Evolution is fast, because it is NOT random: mutations are random, but survival is not.

@aureliengeron @OutSomebod70162 @nattyover I am charmed by how you appear to believe either one of those numbers is a particularly large number. 🤗 If those numbers are as significant as you may think, you should also consider the Fermi Paradox implications! youtu.be/hoeIllSxpEU

Bacteria move around using a molecular machine called the flagellar motor that rotates faster than the flywheel of a race car engine and switches directions in an instant. After 50 yrs, scientists have finally figured out how it works. “My lifelong quest is now fulfilled.” Link⤵️

@OutSomebod70162 @skenzyme @nattyover The Earth is over 4 500 000 000 years old. There are about 5 000 000 000 000 000 000 000 000 000 000 bacteria on Earth, and they reproduce every few hours. Each new bacteria is an opportunity for the evolution of the flagellum. Evolution had time. Please watch the videos.

@aureliengeron @skenzyme @nattyover There is no evidence, there is conjecture. Micro evolution has been observed but evolution on that scale and complexity is mathematically impossible given the number of years.

@skenzyme @OutSomebod70162 @nattyover The videos show that there's plenty of evidence for evolution, both from the historical record and from direct observation, in particular in domesticated species and in the lab. It's like a crime scene with the killer's DNA, fingerprints, and surveillance footage.

@aureliengeron @OutSomebod70162 @nattyover Just Do Stories in vlog form are still Just So Stories, not science. Analogies and inferences make for great bedtime stories though. It’s fine to say, “we don’t know.”

@OutSomebod70162 @nattyover I know it feels that way, but if you watch the Stated Clearly playlist, you'll see that evolution can be immensely creative and beautiful. It's a real eye opener. ♥️

@aureliengeron @nattyover Evolution could never produce this. It requires many things to work all at once.

@prsna01 That's very cool! I'd love to see what the final graph looks like. 👍

Creating my ML notes on obsidian from Hands on Machine learning book by @aureliengeron ....it's fun doing this...and I will going to make full notes of this book on obsidian in a month...I took a challenge so let's go..🔥

@duncanreyburn You might want to read The Righteous Mind by J. Haidt as well. He shows that we tend to decide what to believe based on our education and gut feelings rather than logical arguments. We then cherry pick rational arguments to justify these beliefs. No ideal to get to the truth.

@duncanreyburn So basically any philosopher you disagree with is not a decent philosopher, is that it? Try reading Daniel C. Dennett: his arguments are really quite convincing. For example in Quining Qualia or Consciousness Explained.

No decent philosopher believes ‘machine consciousness’ is (or ever will be) a thing.

@cartright88 Thanks a lot Adam! 🙏

@aureliengeron My copy of HomlP arrives tomorrow. I’ve got 3 of them on my shelves now and learned 80% of what I know from them. You are appreciated @aureliengeron 👏🏻

JEPA are finally easy to train end-to-end without any tricks! Excited to introduce LeWorldModel: a stable, end-to-end JEPA that learns world models directly from pixels, no heuristics. 15M params, 1 GPU, and full planning <1 second. 📑: le-wm.github.io

Yann LeCun and his team dropped yet another paper! "V-JEPA 2.1: Unlocking Dense Features in Video Self-Supervised Learning" In this V-JEPA upgrade, they showed that if you make a video model predict every patch, not just the masked ones AND at multiple layers, they are able to turn vague scene understanding into dense + temporal stable features that actually understands "what is where". This key insight drove improvements in segmentation, depth, anticipation, and even robot planning.

@KaiLiuClemson Ah yes, you're right, thanks, I'll drop one of them. 👍

@aureliengeron Cell 68 and 69 are identical, is it duplicated?

If you're interested in image generation, I just added a simple code example using flow matching at the end of notebook 18: colab.research.google.com/github/ageron/…

@KaiLiuClemson Yes, there was a typo, it's fixed now, sorry!

@aureliengeron Invalid notebook..

@hakalyanpur Oops, that was a typo. It's fixed now, sorry about that.

@nyang20258 Thanks! Yes, the notebook shows how to build and train these models from scratch. It also includes some examples of using a pretrained model using Hugging Face libraries.