Deep Learning
June 14, 2025 at 7:39 PM
Deep Learning
Deep Learning yASSification
March 16, 2026 at 7:28 PM
Deep Learning yASSification
My deep learning course at the University of Geneva is available on-line. 1000+ slides, ~20h of screen-casts. Full of examples in PyTorch.
fleuret.org/dlc/
And my "Little Book of Deep Learning" is available as a phone-formatted pdf (nearing 700k downloads!)
fleuret.org/lbdl/
fleuret.org/dlc/
And my "Little Book of Deep Learning" is available as a phone-formatted pdf (nearing 700k downloads!)
fleuret.org/lbdl/
November 26, 2024 at 6:15 AM
My deep learning course at the University of Geneva is available on-line. 1000+ slides, ~20h of screen-casts. Full of examples in PyTorch.
fleuret.org/dlc/
And my "Little Book of Deep Learning" is available as a phone-formatted pdf (nearing 700k downloads!)
fleuret.org/lbdl/
fleuret.org/dlc/
And my "Little Book of Deep Learning" is available as a phone-formatted pdf (nearing 700k downloads!)
fleuret.org/lbdl/
the deep brain learning is *seriously fucking weird*
September 10, 2024 at 11:28 PM
the deep brain learning is *seriously fucking weird*
Luckily all these guys have a deep capacity for admitting mistakes and learning from them
“I voted for none of this."
Prominent influencers, including Theo Von, Joe Rogan, and Andrew Schulz, are starting to distance themselves from the president they helped propel to the White House.
Story: www.rollingstone.com/politics/pol...
Prominent influencers, including Theo Von, Joe Rogan, and Andrew Schulz, are starting to distance themselves from the president they helped propel to the White House.
Story: www.rollingstone.com/politics/pol...
October 6, 2025 at 8:49 PM
Luckily all these guys have a deep capacity for admitting mistakes and learning from them
I’m very pleased to announce that a preview of the 3rd Edition of Deep Learning with R is now available! mng.bz/X7xa
The book is 50% off through July 8!
The book is 50% off through July 8!
Deep Learning with R, Third Edition
Deep learning from the ground up using R and the powerful Keras library!</b>
Deep Learning with R, Third Edition</i> introduces deep learning from scratch with examples that use the R language and th...
mng.bz
June 20, 2025 at 5:58 PM
I’m very pleased to announce that a preview of the 3rd Edition of Deep Learning with R is now available! mng.bz/X7xa
The book is 50% off through July 8!
The book is 50% off through July 8!
America is learning the hard way that the “deep state” was actually the “deep security blanket” - nameless agencies and workers keeping us safe.
April 7, 2025 at 5:22 AM
America is learning the hard way that the “deep state” was actually the “deep security blanket” - nameless agencies and workers keeping us safe.
Deep learning is hitting a firewall
April 10, 2026 at 6:42 PM
Deep learning is hitting a firewall
Iirc there was a lot of emphasis on Bayesian probabilistic models and RL aimed at direct goals. Definitely underrated Deep Learning as a paradigm.
September 25, 2026 at 5:24 AM
Iirc there was a lot of emphasis on Bayesian probabilistic models and RL aimed at direct goals. Definitely underrated Deep Learning as a paradigm.
My mailbox is literally flooded with discussions of whether “Deep learning is hitting a wall”, almost none of which cite my much-ridiculed-at-the-time 2022 paper called “Deep learning is hitting a wall”.
nautil.us/deep-learnin...
nautil.us/deep-learnin...
Deep Learning Is Hitting a Wall
What would it take for artificial intelligence to make real progress?
nautil.us
November 30, 2024 at 1:21 AM
My mailbox is literally flooded with discussions of whether “Deep learning is hitting a wall”, almost none of which cite my much-ridiculed-at-the-time 2022 paper called “Deep learning is hitting a wall”.
nautil.us/deep-learnin...
nautil.us/deep-learnin...
My new paper "Deep Learning is Not So Mysterious or Different": arxiv.org/abs/2503.02113. Generalization behaviours in deep learning can be intuitively understood through a notion of soft inductive biases, and formally characterized with countable hypothesis bounds! 1/12
March 5, 2025 at 3:38 PM
My new paper "Deep Learning is Not So Mysterious or Different": arxiv.org/abs/2503.02113. Generalization behaviours in deep learning can be intuitively understood through a notion of soft inductive biases, and formally characterized with countable hypothesis bounds! 1/12
This paper argues that a real scientific theory of deep learning is beginning to emerge.
“There Will Be a Scientific Theory of Deep Learning”
Paper: arxiv.org/abs/2604.21691
“There Will Be a Scientific Theory of Deep Learning”
Paper: arxiv.org/abs/2604.21691
April 28, 2026 at 2:13 PM
This paper argues that a real scientific theory of deep learning is beginning to emerge.
“There Will Be a Scientific Theory of Deep Learning”
Paper: arxiv.org/abs/2604.21691
“There Will Be a Scientific Theory of Deep Learning”
Paper: arxiv.org/abs/2604.21691
so I can explain this: it's not generative AI: it's usually deep learning models trained on meteorology tasks and it can be quite effective
I know It would only annoy me, but if you are using weather balloons for data, where does the AI come in?
Because it sounds like they’re just doing meteorology and complicating it with AI.
Because it sounds like they’re just doing meteorology and complicating it with AI.
October 24, 2025 at 4:00 PM
so I can explain this: it's not generative AI: it's usually deep learning models trained on meteorology tasks and it can be quite effective
goooood morning!
grab your coffee and join me for a morning science-deep dive. we’re learning about the science of 👻 ghosts 👻 today!
Twitch.tv/Cheebs
grab your coffee and join me for a morning science-deep dive. we’re learning about the science of 👻 ghosts 👻 today!
Twitch.tv/Cheebs
November 9, 2025 at 4:33 PM
goooood morning!
grab your coffee and join me for a morning science-deep dive. we’re learning about the science of 👻 ghosts 👻 today!
Twitch.tv/Cheebs
grab your coffee and join me for a morning science-deep dive. we’re learning about the science of 👻 ghosts 👻 today!
Twitch.tv/Cheebs
They were focused on reinforcement learning, kind of similar to the deep reinforcement learning work DeepMind pioneered. They spent a lot of time teaching models to play video games, because you can't really get RL to converge with a larger state space. They didn't care about language models at all.
September 25, 2026 at 1:31 PM
They were focused on reinforcement learning, kind of similar to the deep reinforcement learning work DeepMind pioneered. They spent a lot of time teaching models to play video games, because you can't really get RL to converge with a larger state space. They didn't care about language models at all.
Deep down, ChatGPT 4.5 "knows" this too. Here's how it sends me off into my caculus learning journey:
June 7, 2025 at 11:36 AM
Deep down, ChatGPT 4.5 "knows" this too. Here's how it sends me off into my caculus learning journey:
i like learning abt the ocean and deep sea creatures . i dislike being betrayed or slighted
October 22, 2025 at 6:12 AM
i like learning abt the ocean and deep sea creatures . i dislike being betrayed or slighted
Deep learning for proteins tutorial: github.com/Graylab/DL4P...
GitHub - Graylab/DL4Proteins-notebooks: Colab Notebooks covering deep learning tools for biomolecular structure prediction and design
Colab Notebooks covering deep learning tools for biomolecular structure prediction and design - Graylab/DL4Proteins-notebooks
github.com
December 28, 2024 at 3:15 AM
Deep learning for proteins tutorial: github.com/Graylab/DL4P...
Deep learning is eating the wall
December 12, 2024 at 3:46 PM
Deep learning is eating the wall
The role of Canada’s Governor General calls for sound judgement, deep learning, and an unwavering commitment to the rule of law — the very principles which Louise Arbour has built her exceptional career upon.
June 8, 2026 at 7:38 PM
The role of Canada’s Governor General calls for sound judgement, deep learning, and an unwavering commitment to the rule of law — the very principles which Louise Arbour has built her exceptional career upon.
este es mi viaje: I am learning about canceled Mexican influencers several layers of internet deep
February 1, 2025 at 5:06 PM
este es mi viaje: I am learning about canceled Mexican influencers several layers of internet deep
The more deep learning I do, the more I like logistic regression
November 3, 2025 at 1:39 PM
The more deep learning I do, the more I like logistic regression
📣 Latest from the lab: Performance of deep-learning-based approaches to improve polygenic scores www.nature.com/articles/s41...
Its thought deep learning will substantially improve PGS but the reality is MANY have tried but no/little gain has been seen so far. Here we report our negative results.
Its thought deep learning will substantially improve PGS but the reality is MANY have tried but no/little gain has been seen so far. Here we report our negative results.
June 5, 2025 at 1:37 PM
📣 Latest from the lab: Performance of deep-learning-based approaches to improve polygenic scores www.nature.com/articles/s41...
Its thought deep learning will substantially improve PGS but the reality is MANY have tried but no/little gain has been seen so far. Here we report our negative results.
Its thought deep learning will substantially improve PGS but the reality is MANY have tried but no/little gain has been seen so far. Here we report our negative results.
it was always 'generative AI'! since DLSS 1, it's DEEP LEARNING SUPER SAMPLING, the large deep learning model (AI) _generates_ pixel data
March 18, 2026 at 10:18 PM
it was always 'generative AI'! since DLSS 1, it's DEEP LEARNING SUPER SAMPLING, the large deep learning model (AI) _generates_ pixel data
Been learning about SNES fonts & compression recently. The rabbit hole goes deep but very rewarding to figure out
April 29, 2026 at 5:56 PM
Been learning about SNES fonts & compression recently. The rabbit hole goes deep but very rewarding to figure out