Surya Ganguli
@SuryaGanguli
Followers
18K
Following
9K
Media
230
Statuses
3K
Associate Prof of Applied Physics @Stanford, and departments of Computer Science, Electrical Engineering and Neurobiology. Venture Partner @a16z
Stanford, CA
Joined December 2013
RT @lpachter: This week in academia, a not so short🧵. 1. Staff reductions and other cost cutting measures coming to Brown University ht….
0
106
0
This syllabus contains ancient antediluvian wisdom from before the flood of deep learning scaling. Young people would do well to master it. E.g Graphical models are essential in AI for science where interpretability and well calibrated uncertainty quantification is needed. They.
This is the syllabus of the course @geoffreyhinton and I taught in 1998 at the Gatsby Unit (just after it was founded). Notice anything?
3
10
133
RT @MasonKamb: Honored to have had my recent work with @SuryaGanguli on the mechanisms behind creativity in diffusion models featured in th….
0
6
0
A great @QuantaMagazine article on our theory of creativity in convolutional diffusion models lead by @MasonKamb. See also our paper with new results in version 2: to be presented as an oral at @icmlconf #icml25 thx @_webbwright !.
In a recent paper, physicists used two predictable factors to reproduce the “creativity” seen from image-generating AI. @_webbwright reports:
3
8
59
No. Some (biased) counterexamples:. A 2D dynamical system predicting mouse brain activity: Random projections and scaling in the brain: Critical dynamics triggering perception: Random matrix theory and.
Theoretical neuroscience has become a series of self-referential mathematical exercises, untroubled by the messy realities of the brain. It’s now more a subfield of theoretical physics than biology, where the universe is replaced with a collection of neurons and data is optional.
5
21
177
I think it’s even more beautiful if written as e^(i pi) + 1 = 0. Then the additive identity 0 and the multiplicative identity 1 both get brought in to play a role, in addition to differential equations (e), geometry (pi) and algebraic closure (i).
What you see below is one of the most beautiful formulas in mathematics. A single equation, establishing a relation between 𝑒, π, the imaginary number, and 1. It is mind-blowing. This is what's behind the sorcery:
1
1
16
Criminal.
0
2
25
Good advice. Works for achieving long term research goals as well.
0
1
20
These pictures will be amazing! The Legacy Survey of Space and Time is an incredible feat of science and engineering that will.image the entire southern sky every 3 nights for 10 years generating 20TB of data per night, yielding a new window into our universe and how it changes.
Are you ready to #CaptureTheCosmos?. Our LSST Camera has 21 3-by-3 arrays of state-of-the-art imaging sensors to take unprecedented 3,200-megapixel images of the night sky. Join us tomorrow, June 23, 2025 for the first look.
0
3
31
RT @SLAClab: Are you ready to #CaptureTheCosmos?. Our LSST Camera has 21 3-by-3 arrays of state-of-the-art imaging sensors to take unpreced….
0
18
0
RT @KempnerInst: The Kempner Institute's Frontiers in NeuroAI symposium showcased researchers from around the world who are pushing forward….
0
5
0
RT @CodeXStanford: View the opening keynote by @SuryaGanguli at the recent Codex FutureLaw conference @StanfordLaw, where tech and law inte….
0
4
0
The best part of this job is seeing students graduate and launch their careers! Congrats to Feng Chen, Atsushi Yamamura, Tamra Nebabu, Linnie Wharton and Daniel Kunin. They are all going on to top positions across artificial intelligence, medicine, and physics. Proud of you!
1
1
93
The @Stanford biosciences affirmation taken by all of our PhD grads is inspiring, with pledges to:.1) Do science with rigor, integrity, and uncompromising respect for truth.2) Show kindness and compassion to colleagues.3) Show honesty and respect to the public.4) Place public
0
3
47
RT @jakescottMD: RFK Jr. went on national TV and spouted egregious, dangerous falsehoods about vaccines. As a parent and infectious disease….
0
10K
0
No way! ;).
i'm almost sure that most ML engineers don’t know that diffusion models come from thermodynamics. the forward process is inspired by non-equilibrium thermodynamics: data is gradually perturbed by gaussian noise, forming a markov chain, governed by a discretized fokker-planck
1
4
85
Had fun presenting at @Harvard's @KempnerInst on Theories of rapid learning, creativity, and reasoning: of mice and machines.Video: Papers:.Rapid learning: Creativity: Math reasoning:
NEW: @SuryaGanguli of @Stanford presenting computational insights into the neural basis of learning, reasoning and imagination. Watch the talk: #NeuroAI2025 #neuroscience #ML #NeuroAI
1
11
107