CCN: Publications

Task-Induced Representational Invariances Depend on Learning Objective in Deep RL

Manu Srinath Halvagal, S. Lee, S. Chung

Two Speeds of Learning: A Representation-Readout Decomposition of Grokking and Double Descent

C. Chou , Oscar Uzdelewicz, Neng-Chun Chiu, Yao-Yuan Yang, S. Chung

Learning Normalized Energy Models for Linear Inverse Problems

Nicolas Zilberstein, Santiago Segarra, E. P. Simoncelli, F. Guth

How Data Augmentation Shapes Neural Representations

Tianxiao He, A. Williams, S. Harvey

Tracking the Fidelity of Internal Neural Representations with Error-In-Variables Regression

Isabel Garon, Stephen Keeley, A. Williams

There Will Be a Scientific Theory of Deep Learning

Jamie Simon, Daniel Kunin, Alexander Atanasov, Enric Boix-Adser`, Blake Bordelon, J. Cohen, N. Ghosh, F. Guth, Arthur Jacot, Mason Kamb, Dhruva Karkada, Eric J. Michaud, Berkan Ottlik, Joseph Turnbull

Modulating Cross-Modal Convergence with Single-Stimulus, Intra-Modal Dispersion

Eghbal A. Hosseini, Brian Cheung, Evelina Fedorenko, A. Williams

Reproducibility and model-selection stability in connectome-constrained circuit modeling

Christos Karaneen, E. Schomburg, D. Chklovskii

Estimating Dimensionality of Neural Representations from Finite Samples

C. Chun, A. Canatar, S. Chung , Daniel Lee

Quasi Monte Carlo methods enable extremely low-dimensional deep generative models

Miles Martinez, A. Williams