Manish
@algorithm_ml
Machine learning & Computer science function approximation
11 articles & papers we read this month 👇 1. ChatGPT and the Meaning of Life - @LedermanHarvey scottaaronson.blog/?p=9030
You should switch to the 2025 edition, which uses Keras 3 and JAX in addition to TF and torch. It's available online for free deeplearningwithpython.io The 2021 content is largely still relevant, mind you, but the 2025 content is better.
For anyone getting started with deep learning in 2025 and looking to do large scale training: use JAX + Keras 3. Unless you like suffering.
The essence of great software is the quality of its abstractions. Great abstractions are indefinitely composable and stackable. They become a dependable foundation for future work, future thought. The best ones are so robust you never have to revisit them -- you can forget them…
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!
One thing about intelligence though, is that it helps you get to that threshold faster, with less practice.
The bottleneck for deep skill isn't usually intelligence, but boredom tolerance. Learning has an activation energy: below a certain skill threshold, practice is tedious, but above it, it becomes a self-sustaining flow state. The entire battle is persisting until that transition.
🤔What you’ll get from this monograph: A clear and systematic walkthrough of how diffusion models emerged, how the main formulations connect, and how today’s methods achieve controllability and speed, leading to the next generation of diffusion-based generative models: the…
A powerful idea from @stephen_wolfram: The physics you observe depends on how you are constructed as an observer.
Dostoevsky, a lifetime of wisdom in one paragraph
Fear kills more dreams than failure ever will.
Tired to go back to the original papers again and again? Our monograph: a systematic and fundamental recipe you can rely on! 📘 We’re excited to release 《The Principles of Diffusion Models》— with @DrYangSong, @gimdong58085414, @mittu1204, and @StefanoErmon. It traces the core…
if you go to the gym to stay fit you should be willing to think to stay sharp
Pursue a domain you love, but simultaneously get so insanely technically skilled at math/coding that you can apply it to your domain of interest in an innovative way. Deep domain expertise plus alien-level technical skills equals lots of interesting/rewarding work to do.
"Mathematics is not about numbers, equations, computations, or algorithms: it is about understanding." - William Paul Thurston
Alex Conley, who has a spinal cord injury, was the 2nd patient to undergo neurosurgery at Barrow to receive @Neuralink's N1 Implant as part of the PRIME Study. Now, also enrolled in CONVOY, Alex is the 1st to use the brain-computer interface (BCI) device to control a robotic arm.
Failing to Understand the Exponential, Again? My conversation with @Mononofu - Julian Schrittwieser (@AnthropicAI, AlphaGo Zero, MuZero) - on Move 37, Scaling RL, Nobel Prize for AI, and the AI frontier: 00:00 - Cold open: “We’re not seeing any slowdown.” 00:32 - Intro —…
United States Тренды
- 1. Lamine 58.9K posts
- 2. Barca 95.3K posts
- 3. Godzilla 23.7K posts
- 4. Brujas 22.2K posts
- 5. Trench 7,223 posts
- 6. Barcelona 143K posts
- 7. Brugge 43.6K posts
- 8. $DUOL 2,244 posts
- 9. Shabbat 2,168 posts
- 10. Foden 19.2K posts
- 11. Flick 35K posts
- 12. Richardson 3,346 posts
- 13. Jared Golden 1,687 posts
- 14. Frey 26K posts
- 15. Anthony Taylor 1,613 posts
- 16. Balde 12K posts
- 17. Fermin 11K posts
- 18. Lina Khan 6,681 posts
- 19. Hefner 1,186 posts
- 20. Minneapolis 58.2K posts
Something went wrong.
Something went wrong.