6 citations · 8 across the 7 of their papers we have counts for
7 papers
Contrast encodes inductive bias: separating slow noise from dynamics in predictive representation learning
Paarth Gulati, Ilya Nemenman
Self-supervised methods that learn representations and predict dynamics fully in the latent space, such as JEPA, have been shown to confuse slowly varying noise with the dynamical…
Random neural networks match observed dimensionality of neural population recordings and motivate stronger experimental tests
Zehui Zhao, Michael J Pasek, Ilya M Nemenman
Randomly connected neural networks have long served as a theoretical tool for studying collective dynamics in neural populations, yet quantitative comparisons to experiments remain…
DustNET: enabling machine learning and AI models of dusty plasmas
Zhehui Wang, Justin C. Burton, Niklas Dormagen +30
Dusty plasmas are ubiquitous throughout the universe, spanning laboratory and industrial plasmas, fusion devices, planetary environments, cometary comae, and interstellar media. De…
Distribution of singular values in large sample cross-covariance matrices
Arabind Swain, Sean Alexander Ridout, Ilya Nemenman
For two large matrices and with Gaussian i.i.d.\ entries and dimensions and , respectively, we derive the probability distrib…
Machine learning that predicts well may not learn the correct physical descriptions of glassy systems
Arabind Swain, Sean Alexander Ridout, Ilya Nemenman
The complexity of glasses makes it challenging to explain their dynamics. Machine Learning (ML) has emerged as a promising pathway for understanding glassy dynamics by linking thei…
Quantifying evolvability in small biological networks
Andrew Mugler, Etay Ziv, Ilya Nemenman +1
We introduce a quantitative measure of the capacity of a small biological network to evolve. We apply our measure to a stochastic description of the experimental setup of Guet et a…