Yasaman Bahri
@yasamanbb
Followers
5K
Following
5K
Statuses
316
Research Scientist @GoogleDeepMind // Neural networks & AI, stat physics, condensed matter // Ph.D. theoretical physics @UCBerkeley.
SF Bay Area
Joined November 2014
A wonderfully organized school in an inspiring and didactic setting! Lecture notes from the Les Houches summer school are now published. Boris Hanin & I lectured on the theory of neural networks at large width.
The long-awaited collection of lecture notes from the Summer School on Statistical Physics & Machine Learning, Les Houches 2022, is now published in JStatMech . I am particularly proud of the works the school inspired; see section 3 of the editorial.
0
3
37
RT @slaterstich: Very excited to share our interview with @jaschasd on the history of diffusion models — from his original 2015 paper inven…
0
50
0
What an exciting week it's been ...! Huge congrats for work done at DeepMind.
Huge congratulations to @DemisHassabis and John Jumper on being awarded the 2024 Nobel Prize in Chemistry for protein structure prediction with #AlphaFold, along with David Baker for computational protein design. This is a monumental achievement for AI, for computational biology, and science itself. 🧬
0
0
30
RT @MBarkeshli: John Hopfield has a nice article in the annual reviews of condensed matter physics. It starts off with a discussion of what…
0
177
0
RT @DimaKrotov: Given today’s great news from the #NobelPrize2024, I want to share a couple of personal thoughts on Hopfield Networks. Thi…
0
114
0
RT @SuryaGanguli: Congrats to John Hopfield and @geoffreyhinton! well deserved recognition that some important foundations of AI rest on ph…
0
53
0
@PedramRoushan @GoogleQuantumAI @UCSBPhysics @karamlouMIT Congratulations Pedram & team! 👏👏 A remarkable journey.
0
0
2
Part of a special feature by PNAS on physics & machine learning.
1
0
7
This was a great collaboration between Google DeepMind, Google Research, Harvard Physics/SEAS, & Cornell Physics (in particular noting first author Haining Pan, Michael Brenner, & Eun-Ah Kim @eunahkim).
0
1
6
Among interesting findings I’d highlight two in particular. (i) We can categorize calculation steps into whether the results appears in the paper explicitly (since intermediate steps are often missing). We find the performance is fairly insensitive to this
1
0
5