Haim Sompolinsky (@HSompolinsky) / X

Haim Sompolinsky

57 posts

Haim Sompolinsky

@HSompolinsky

@Harvard Professor of MCB & Physics and Director of Swartz Program in Theoretical Neuroscience; @HebrewU Professor of Physics and Neuroscience (Emeritus)

Joined July 2018

Haim Sompolinsky
@HSompolinsky
Mar 25, 2021
I am excited to announce a new work by an outstanding PhD student Ben Sorscher from Ganguli Lab that links the geometry of neural representations to one of most remarkable cognitive human abilities, learning new concepts from only few examples. biorxiv.org/content/10.110…
Haim Sompolinsky
@HSompolinsky
Oct 6, 2021
Qianyi Li and I are excited to announce the publication of our paper on the Kernel Renormalization Theory of Deep Learning in Phys Rev X link.aps.org/doi/10.1103/Ph… . We derive an exact stat mech solution of deep learning by successive integration of weights
Haim Sompolinsky
@HSompolinsky
Mar 29, 2024
the title of LeCun's slide says it all.
147K
Haim Sompolinsky
@HSompolinsky
Oct 30, 2022
Our work on manifold geometric theory underlying fast learning of novel concepts led by Ben Sorcher of the Ganguli Lab is out. pnas.org/doi/pdf/10.107… We apply our theory to object manifold representations in deep neural network (DNN) and in macaque IT cortex.
Haim Sompolinsky
@HSompolinsky
Mar 16, 2022
#cosyne22 Open position for a phd or postdoc in theory at the interface of deep learning and neuroscience. If you have suitable background please see me at the meeting.
Haim Sompolinsky
@HSompolinsky
Jun 5, 2019
1/ A new paper provides the first, theory-based measurement of the untangling of object manifolds by several ImageNet trained DCNNs, using ImageNet point-cloud manifolds and smoothly warped images. biorxiv.org/content/10.110…
Haim Sompolinsky
@HSompolinsky
Jan 8, 2024
My Harvard/Neuro 231, 2024 Edition begins soon. It explores contemporary brain theory spanning local neuronal circuits as well as deep neural networks. It examines the relationship between network structure, dynamics, and computation. 1/3
24K
Haim Sompolinsky
@HSompolinsky
Oct 6, 2022
Postdoc position in Sompolinsky Group: If you are interested in doing exciting postdoc research at Harvard at the forefront of computational neuroscience and the interface between natural and artificial intelligence, send application and 3 letters to [email protected]
Haim Sompolinsky
@HSompolinsky
Mar 29, 2024
Thanks, Yann for the great inspiring talk at Harvard.
195K
Haim Sompolinsky
@HSompolinsky
Dec 19, 2022
I am excited to announce the publication of the wonderful paper of Julia Steinberg on Associative memory of structured knowledge in scientific reports nature.com/articles/s4159…. Most neural models of associative memory store structureless knowledge as simple random patterns in RNNs
22K
Haim Sompolinsky
@HSompolinsky
Sep 18, 2023
I am excited to announce a recent work by Yehonatan Avidan and Qianyi Li arxiv.org/abs/2309.04522 presenting an analytical theory for learning dynamics in infinitely wide neural network.
arxiv.org
Connecting NTK and NNGP: A Unified Theoretical Framework for Wide...
Artificial neural networks have revolutionized machine learning in recent years, but a complete theoretical framework for their learning process is still lacking. Substantial advances were...
10K
Haim Sompolinsky
@HSompolinsky
Dec 9, 2020
I am excited to announce a recent work with Harvard student Qianyi Li deriving exact Stat Mech theory of Deep Linear Neural Networks following supervised learning, revealing exquisite richness of generalization properties and layerwise representations
arxiv.org
Statistical Mechanics of Deep Linear Neural Networks: The...
The success of deep learning in many real-world tasks has triggered an intense effort to understand the power and limitations of deep learning in the training and generalization of complex tasks,...
Haim Sompolinsky
@HSompolinsky
Jul 16, 2018
Most significant advance in stat mech of learning since Gardner. For the first time theory incorporates the rich structure of realistic data.
SueYeon Chung
@s_y_chung
Jul 10, 2018
A new theory to analyze neural manifolds in high-dimensional data. We link the geometry of neural manifolds to their classification capacity. Exciting implications on understanding deep networks and sensory systems! With Haim Sompolinsky and Dan Lee. go.aps.org/2tVHcYm
Haim Sompolinsky
@HSompolinsky
Feb 20, 2020
The Swartz Program at Harvard University seeks applications for postdoctoral fellows in theoretical and computational neuroscience. Please send application material to [email protected] and come to see me at Cosyne 2020.