Yann LeCun
@ylecun

Professor at NYU. Chief AI Scientist at Facebook. Researcher in AI, Machine Learning, etc. ACM Turing Award Laureate.




Yann LeCun    @ylecun
Largest private funding round ever for a biotech startup in Canada. Congrats @frey_brendan and the @deepgenomics team.

Yann LeCun    @ylecun
2 more lectures from the Spring'21 NYU Deep Learning course. Energy-Based Model, a general framework to describe most ML/stat methods, whether probabilistic or not, supervised, weakly sup, self-sup, or unsup, contrastive or not, with latent variables or not, generative or not.

Yann LeCun    @ylecun
Toronto-based @deepgenomics raises $180M in C round. Congrats @frey_brendan ! Thrilled to be on your Scientific Advisory Board.

Yann LeCun    @ylecun
Modern number notation. Algebra, trigonometry, calculus. Optics. Atomic theory, thermodynamics, and chemistry. Thermal engines. Electricity and electromagnetism. Computation. Basically: first 3 years of undergraduate engineering program.

Yann LeCun    @ylecun
Barlow Twins!

Yann LeCun    @ylecun
Another lecture of NYU Deep Learning, Spring 2021is available. @alfcnz gave me magic fingers.

Yann LeCun    @ylecun
Congrats @tydsh @endernewton and @SuryaGanguli ! The paper explains why/how some non-contrastive self-supervised methods for joint embedding architectures (e.g. BYOL) actually work and manage to avoid collapse despite having no explicit provision to do so.

Yann LeCun    @ylecun
85% of FB users have been or want to be vaccinated. Many countries that use FB as much as the US have much lower level of anti-vaxxers. The cause of anti-vaxx sentiment in the US is not social media. In fact FB has done a lot to promote vaccinations, as Guy Rosen writes here.

Yann LeCun    @ylecun
BlenderBot 2.0: the first chatbot that can hold a conversation on any topic. It has a long term memory and can search for information on the Internet.

Yann LeCun    @ylecun
Pantheon of scientific territorial hubris: Chemistry is just physics Biology is just chemistry Neuroscience is just biology Psychology is just neuroscience Economics is just psychology Computer science is just math Machine learning is just statistics All of it is just philosophy!
 Reply      Retweet   35      Like    186   

Yann LeCun    @ylecun
Obviously true. Text is a low-bandwidth channel, much lower bandwidth than the experience of the physical world. The *vast* majority of human knowledge about how the world works is not expressed in any text. Text merely reflects a very thin sliver of high-level human knowledge.

Yann LeCun    @ylecun
The first 2 weeks of the 2021 edition of the NYU Deep Learning course are now on line, including lectures, practicum, homework, etc.

Yann LeCun    @ylecun
Note: even in the late 1980s, I was in the "Early 2020s" category. The time it took to train the "ConvNet du jour" on the "problem du jour" has consistently been around 10 days over the last 33 years. This is independent of compute power and data.

Yann LeCun    @ylecun
Interesting tutorial next week by @HazanPrinceton. I'd say: "RL is control without gradients and (mostly) without models" Since control preceded RL, we could view RL as a "degraded" version of on-line stochastic optimal control where the objective is not differentiable.

Yann LeCun    @ylecun
ML researchers: Late 1990s: "Method X is bad because the loss is non convex, there are no generalization bounds, and it's not properly regularized" Early 2020s: "Method X is non convex, has no generalization bound, and is wildly over-parameterized. But it works great!"

Yann LeCun    @ylecun
ML researchers: Late 1990s: "Method X is worthless because the Matlab code takes more than 20 minutes to converge" Early 2020s: "Method X is great because with <favorite_DL_framework>, I can train it on 10 billion samples using 1000 {GPU,TPU}s in less than a week."

Yann LeCun    @ylecun
Now, by "new paradigms", I mean new learning paradigms. And there is no doubt that they will involve some sort of gradient-based optimization applied to complex architectures (aka "deep learning"). The "new" part should focus on learning world models in a task independent way.

Yann LeCun    @ylecun
We do not have an answer to that question, and the gap to bridge is enormous (how can people learn to drive a car in 20h of practice?) Decisive advances towards an answer will mark a new era in AI. That's why I work on self-supervised learning. It's our best shot at the moment.

Yann LeCun    @ylecun
So many exciting new frontiers in ML, it's hard to give a short list, particularly in new application areas (e.g. in the physical and biological sciences). But the Big Question is: "How could machines learn as efficiently as humans and animals?" This requires new paradigms.

Yann LeCun    @ylecun
A new large-scale language model that can predict the effect of mutations on the function of a protein. By the FAIR+NYU Protein research group led by @alexrives .

Yann LeCun    @ylecun
An article at Forbes about new research at FAIR on AI for robotics. https://t.co/UPC4Abo2k0

Yann LeCun    @ylecun
A blog post detailing the new work on Rapid Motor Adaptation for legged robot locomotion from FAIR+BAIR+CMU https://t.co/7l2CK54Ehs

Yann LeCun    @ylecun
Rapid Motor Adaptation: great new work on adaptive robot locomotion from FAIR+BAIR+CMU.

Yann LeCun    @ylecun
Predatory academic publishers must die. In fact, for-profit academic publishers must go away. Even non-profit publishers that are not open access must disappear, or else change their economic model. Look at JMLR, ICLR, NeurIPS, ICML: all free and open access with no fees.
 Reply      Retweet   20      Like    103   

Yann LeCun    @ylecun
Moral of the story: the patent system can be very counterproductive when patents are separated from the people best positioned to build on them. Patents make sense for certain things, mostly physical things. But almost never make sense for "software", broadly speaking. 9/N, N=9

Yann LeCun    @ylecun
It wasn't until I left AT&T in early 2002 that I restarted work on ConvNets. I was hoping that no one at NCR would realize they owned the patent on what I was doing. No one did. I popped the champagne when the patents expired in 2007! 🍾πŸ₯‚ 8/N

Yann LeCun    @ylecun
So I stopped working on ML. Neural nets were becoming unpopular anyways. I started a project on image compression for the Web called DjVu with Léon Bottou. And we wrote papers on all the stuff we did in the early 1990s. 7/N

Yann LeCun    @ylecun
The first deployment actually took place a year before that in ATM machines for amount verification (first deployed by the Crédit Mutuel de Bretagne in France). Then in 1996, catastrophe strikes: AT&T split itself up into AT&T (services), Lucent (telecom equipment), and NCR. 4/N

Yann LeCun    @ylecun
A complete check reading system was eventually built that was reliable enough to be deployed. Commercial deployment in banks started in 1995. The system could read about half the checks (machine printed or handwritten) and sent the other half to human operators. 3/N

Yann LeCun    @ylecun
We started working with a development group that built OCR systems from it. Shortly thereafter, AT&T acquired NCR, which was building check imagers/sorters for banks. Images were sent to humans for transcription of the amount. Obviously, they wanted to automate that. 2/N

Yann LeCun    @ylecun
There were two patents on ConvNets: one for ConvNets with strided convolution, and one for ConvNets with separate pooling layers. They were filed in 1989 and 1990 and allowed in 1990 and 1991. 1/N
 Reply      Retweet   13      Like    74   

Yann LeCun    @ylecun
This is part of a 10-year project that involved some 3D data collection (with drones and all) and some 3D reconstruction wizardry from Jean Ponce and his collaborators. More info on the project here: https://t.co/4MIfdKxHIj 2/N

Yann LeCun    @ylecun
A *fantastic* interactive website showing a navigable 3D reconstruction of Villa Diomedes in Pompeii. You can navigate the archeological site and smoothly blend the current state of the remains with the way it looked at the time it was inhabited. 1/N https://t.co/eYkR5PCHMU
 Reply      Retweet   23      Like    63   











 








Yann LeCun

hardmaru

Facebook AI

Lex Fridman

Sergey Levine

DeepMind