Abdulkadir Canatar

154 posts

Abdulkadir Canatar

Abdulkadir Canatar

@canatar_a

Research Fellow @FlatironCCN. Theoretical Neuroscience, Machine Learning, Physics. Prev: @Harvard and @sabanciu

New York, NY Katılım Haziran 2013
906 Takip Edilen333 Takipçiler
Abdulkadir Canatar retweetledi
Chanwoo Chun
Chanwoo Chun@ChunChanWoo·
🚀 New at #ICLR2026 (ranked 71 / 20,000, top 0.358% by reviewer score): We show how to estimate the dimensionality of an impossibly large matrix from only tiny submatrices or sparse observations. Presenting next month in Brazil 🇧🇷
English
1
1
6
233
Abdulkadir Canatar retweetledi
Physical Review E
Physical Review E@PhysRevE·
A new statistical mechanics framework quantifies how the geometrical properties of neuronal representation affect continuous decoding of tasks and task performance — a key question in computational #neuroscience and with implications for #DeepLearning. go.aps.org/41nt9L0
Physical Review E tweet media
English
2
18
41
2K
Abdulkadir Canatar retweetledi
Cengiz Pehlevan
Cengiz Pehlevan@CPehlevan·
Very excited to be a part of this amazing collaboration! Thanks @SimonsFdn for the support!
Simons Foundation@SimonsFdn

Our new Simons Collaboration on the Physics of Learning and Neural Computation will employ and develop powerful tools from #physics, #math, computer science and theoretical #neuroscience to understand how large neural networks learn, compute, scale, reason and imagine: simonsfoundation.org/2025/08/18/sim…

English
3
6
79
9K
Abdulkadir Canatar retweetledi
Alex Atanasov
Alex Atanasov@ABAtanasov·
If you’re an undergrad interested in shaping the future of AI, you can either fine-tune underwhelming language models at a leading AI lab OR you can join the group of one of the most talented scientists I know, pursuing some of the most promising research at the intersection of AI, Neuro, Scaling, and Statistical Physics
Blake Bordelon ☕️🧪👨‍💻@blake__bordelon

Excited to announce that I will be joining @UTAustin with a joint position between @OdenInstitute for Computational Science and dept of Neuroscience in FL 2026! I plan on recruiting PhD students and postdocs interested in mathematics of neural computation (more details to come).

English
0
6
55
13.6K
Blake Bordelon ☕️🧪👨‍💻
Blake Bordelon ☕️🧪👨‍💻@blake__bordelon·
Excited to announce that I will be joining @UTAustin with a joint position between @OdenInstitute for Computational Science and dept of Neuroscience in FL 2026! I plan on recruiting PhD students and postdocs interested in mathematics of neural computation (more details to come).
Blake Bordelon ☕️🧪👨‍💻 tweet media
English
34
16
339
48K
Abdulkadir Canatar retweetledi
SueYeon Chung
SueYeon Chung@s_y_chung·
🧵0/7 🚨 Spotlight @ICML2025 🚨 Chi-Ning and Hang have been thinking deeply about how feature learning reshapes neural manifolds, and what that tells us about generalization and inductive bias in brains and machines. They put together the thread below, which I’m sharing on their behalf 👇Enjoy!
SueYeon Chung tweet media
English
4
40
229
25K
Abdulkadir Canatar retweetledi
Fatih Dinc
Fatih Dinc@fatihdin4en·
As we say in Turkish "Yasasin 23 Nisan!" BTF is now officially accepting funding applications for summer research internships: bridgetoturkiye.org/our-work/schol… The program requires you to apply with a mentor, who can be a PhD or a postdoc in a US institution. Good luck!
Fatih Dinc@fatihdin4en

Announcement of a new scholarship program for Turkish students seeking internships in the US! (currently accepting donations) In early 2025, BTF (bridgetoturkiye.org) will be opening a new scholarship program to support research scholars (anyone prior to PhD) with their summer internship costs. If you like to support the future PhD students, please consider donating below. On December 3, for 24 hours only, BTF will match every donation made to Giving Tuesday fundraisers at a 1:3 ratio—tripling your support. Donations up to $1,000 will be matched, with a total matching pool of up to $50,000. Don’t miss this opportunity to make a difference! Link: secure.givelively.org/donate/bridge-…

English
0
11
45
9.7K
Abdulkadir Canatar retweetledi
Özgür Özel
Özgür Özel@eczozgurozel·
Tayyip Erdoğan’a helal olan millete haram olamaz! Boykot demokratik haktır. 2008’de medya boykotu başlatan Erdoğan’ın ta kendisidir. Bugün boykotu kötüleyen şuursuzlar baş kötünün müritleridir. Tutarsızlıktan utanmayanlar, yalandan medet umanlar yine rezil oldunuz. Hadi buyrun…
Türkçe
3.6K
15.6K
89K
3.2M
Abdulkadir Canatar retweetledi
Stat.ML Papers
Stat.ML Papers@StatMLPapers·
Estimating Neural Representation Alignment from Limited Inputs and Features ift.tt/FCidqAR
English
0
2
9
1K
Abdulkadir Canatar retweetledi
SueYeon Chung
SueYeon Chung@s_y_chung·
NYU-CDS article about MMCR (Maximum Manifold Capacity Representations): The key principle of MMCR is to maximize the number of image manifolds (generated by nuisance variations) that can be linearly decoded in the representations, hence maximizing the efficiency of the representation from the perspective of a decoder ('task-centric' efficient coding, or efficient 'decoding', but groups of responses defining a 'manifold' are variations of the same image, so it also has to do with efficiently representing stimuli). The original idea of 'Manifold Capacity' comes from statistical mechanical analysis of the capacity of perceptrons, generalized from discrete points to 'neural manifolds'. very nice to see the interaction between different fields: from a new theory (merging statistical physics, high-dim geometry and convex optimization) to a new SSL algorithm, a new brain model, and new theoretical analyses. Check out the information-theoretic analysis of MMCR: arxiv.org/abs/2406.09366 Original MMCR paper: openreview.net/pdf?id=og9V7Ng… Original paper on Manifold Capacity: journals.aps.org/prx/pdf/10.110…
NYU Center for Data Science@NYUDataScience

CDS researchers @ziv_ravid and @ylecun, et al, advance an entirely new kind of self-supervised learning: Maximum Manifold Capacity Representations (MMCR). MMCR breaks away from traditional SSL methods, though still connects with them via info theory. nyudatascience.medium.com/maximum-manifo…

English
0
13
66
9.8K
Abdulkadir Canatar retweetledi
Simons Institute for the Theory of Computing
Simons Institute for the Theory of Computing@SimonsInstitute·
We mourn the loss of our friend and founding benefactor, Jim Simons. Jim was visionary, brilliant, and generous beyond measure. He has left an indelible mark on our field.
Simons Institute for the Theory of Computing tweet media
English
18
127
781
74.5K
Abdulkadir Canatar retweetledi
Simons Foundation
Simons Foundation@SimonsFdn·
It is with great sadness that the Simons Foundation announces the death of its co-founder and chair emeritus, James Harris Simons. Jim was an award-winning mathematician, a legendary investor and a generous philanthropist. simonsfoundation.org/2024/05/10/sim…
Simons Foundation tweet media
English
313
1.5K
5.7K
2.6M
Abdulkadir Canatar retweetledi
Alex Atanasov
Alex Atanasov@ABAtanasov·
[1/n] Thrilled that this project with @jzavatoneveth and @cpehlevan is finally out! Our group has spent a lot of time studying high dimensional regression and its connections to scaling laws. All our results follow easily from a single central theorem 🧵 arxiv.org/abs/2405.00592
English
5
27
113
22.2K
Abdulkadir Canatar retweetledi
SueYeon Chung
SueYeon Chung@s_y_chung·
🔥Lots of new theories on day 3 of Cosyne: [3-100] capacity for nonlinear classification of manifolds [3-105] theory of multitask learning (optimal repr geometry + geometric measures for data analysis) [3-167] tuning diversity shapes efficient representation geometry 🧵👇🏻
SueYeon Chung@s_y_chung

[3/2] Saturday  (Poster #3-100) @ 12:30-3:45pm. “Context-dependent Nonlinear Classification of Neural Representations” By Francesca Mignacco @framigna, Chi-Ning Chou TL;DR - Theory of nonlinear separation of neural manifolds, using context-dependence and gating mechanisms (5/n)

English
0
5
25
4.7K
Abdulkadir Canatar retweetledi
SueYeon Chung
SueYeon Chung@s_y_chung·
👋Check out the latest findings from our lab at #COSYNE24 @CosyneMeeting Thread & links to preprints to follow (1/n)🧵👇
SueYeon Chung tweet media
English
1
3
63
7.6K
Abdulkadir Canatar retweetledi
SueYeon Chung
SueYeon Chung@s_y_chung·
Just arrived in New Orleans for #NeurIPS2023 this week. Topics I am excited about: neuro-AI, neural manifolds (representation geometry), stat physics for machine learning, interpretability, relational & causal representations My group is presenting their awesome work👇 (1/n)
SueYeon Chung tweet media
English
2
15
113
14K
Abdulkadir Canatar retweetledi
Jenelle Feather
Jenelle Feather@jenellefeather·
At #NeurIPS2023? Interested in brains, neural networks, and geometry? Come by our **Spotlight Poster** Tuesday @ 5:15PM (#1914) on A Spectral Theory of Neural Prediction and Alignment. w/ @canatar_a @s_y_chung @AlbertWakhloo
Jenelle Feather tweet media
Jenelle Feather@jenellefeather

How do the spectral properties of a model influence neural prediction benchmarks? Check out our *new* paper, “A Spectral Theory of Neural Prediction and Alignment,” accepted to #NeurIPS2023 as a spotlight! arxiv.org/abs/2309.12821 w/ @canatar_a @s_y_chung @AlbertWakhloo 🧵1/11

English
2
10
92
12.9K
Abdulkadir Canatar retweetledi
Alex Williams
Alex Williams@ItsNeuronal·
Short thread about our work at #NeurIPS2023. Topics include: - representational similarity - high-D covariance estimates - noise correlations / stochastic representation - optimal transport - scientific applications of deep nets to audio data + social neuro Details below👇
Alex Williams tweet media
English
1
14
89
17.4K

Keşfet

@SimonsFdn @blake__bordelon @UTAustin @OdenInstitute @ICML2025 @s_y_chung @Harvard @hseas