![Eero Simoncelli Profile](https://pbs.twimg.com/profile_images/1722450168824414208/rOC3WOja_x96.jpg)
Eero Simoncelli
@EeroSimoncelli
Followers
1K
Following
3K
Statuses
101
Professor at NYU; Scientific Director, Ctr for Computational Neurocience, Flatiron Institute. Research in Computational Vision (neurons, perception, machines).
New York, NY
Joined February 2022
@liyzhen2 Recent paper focusing on priors: “Generalization in diffusion models…” Outstanding paper award at #ICLR2024 In collaboration with @ZKadkhodaie @FlorentinGuth @StephaneMallat
1
1
9
@GalperinDaniel @neur_reps Daniel- The workshop recording is available online: This may require a neurips login
1
0
0
Graduate students and advanced undergraduates: Interested in a 3-month summer research internship in Computational Neuroscience @FlatironCCN Come join us in June! Application deadline 17 Jan 2025:
2
45
130
RT @BernieSanders: Elon Musk, the richest man in the world, is threatening to unseat elected officials if they do not follow his orders to…
0
38K
0
Heteroscedasticity (spatial fluctuations of variance) accounts for sparsity in images… “Modeling multiscale subbands of photographic images with fields of Gaussian scale mixtures”
Heteroscedasticity refers to a condition in regression analysis where the variance of the error terms, or residuals, is not constant across all levels of the independent variables. In other words, the spread of the residuals changes systematically with the values of the predictors. This violates the assumption of homoscedasticity, which states that residuals should have constant variance. #Statistics #DataScience #Research #Science
0
1
18
RT @EeroSimoncelli: Looking for a PhD program where you can study vision from different perspectives (computer vision, neuroscience, percep…
0
80
0
RT @EeroSimoncelli: Looking for a PhD program where you can study computational neuroscience? NYU has a fantastic array of researchers cov…
0
18
0
RT @ItsNeuronal: There are multiple faculty positions in theoretical/computational neuroscience open this year at NYU. One in the Center f…
0
43
0
RT @FlorentinGuth: I'm delighted to announce that the rainbow 🌈 paper has been accepted at JMLR! ➡️ updated paper with brand new intro: htt…
0
15
0
RT @CMZiemba: The long gestating final chapter of my thesis is out in @SfNJournals this week as a featured cover article. Thanks to all…
0
25
0
RT @sucholutsky: Applications now open for the NYU CDS faculty fellow positions (I'm currently a faculty fellow here), it's a really great…
0
24
0
RT @apeyrache: Deeply saddened by the passing of Yves Frégnac. His scientific legacy is immense. My thoughts are with his family during thi…
0
6
0
RT @ZKadkhodaie: How do we sample from conditional densities with diffusion models, without estimating the exact conditional score? Check…
0
28
0
RT @KanakaRajanPhD: The new Rajan lab website is now LIVE 🚀 I’m excited to officially (re)introduce our lab as part of @harvardmed & @Kemp…
0
31
0
Tks @nikparth1 - @gershbrain that ICLR-2017 paper had 2 contains: (1) End-to-end rate-distortion objective (form of VAE) achieves SoA img compression. (2) Network is only 3 stages, each with local gain control, ubiquitous in biological sensory systems:
@gershbrain My favorite example is image compression: The use of local gain control specifically for compression is heavily inspired by early visual biological computations in retina and LGN and given DL history we were moving away from using these nonlinearities.
0
0
16
RT @dlipshutz: I'm thrilled to share that I'm joining @bcm_neurosci as an asst prof starting Jan 2025! My group is broadly interested in h…
0
17
0
Wow- fantastic! Congratulations John and Geoff!!
BREAKING NEWS The Royal Swedish Academy of Sciences has decided to award the 2024 #NobelPrize in Physics to John J. Hopfield and Geoffrey E. Hinton “for foundational discoveries and inventions that enable machine learning with artificial neural networks.”
0
0
27
RT @NobelPrize: 2024 physics laureate Geoffrey Hinton used a network developed by his co-laureate John Hopfield as the foundation for a new…
0
1K
0