Skip to content
conftrace_

Ben Sorscher

4 papers · 2019–2022 · 1 venue · across top CS/AI venues

Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.

Venues

NeurIPS (4)

Top co-authors

Surya Ganguli (3) Gabriel Mel (2) Daniel D. Lee (1) Shashank Shekhar (1) Haim Sompolinsky (1) Aran Nayebi (1) Robert Geirhos (1) Alexander Attinger (1) Caitlin S Mallory (1) Samuel Ocko (1)

Research topics

Machine Learning (4) Deep Learning (3) Optimization & Theory (3) Artificial Intelligence (2) Architectures (2) Application Areas (1) Core AI (1) Core Methods (1) Learning Paradigms (1) Learning Types · Machine Learning (1) Learning Types · Deep Learning (1)

Keywords

grid cell (2) representation learning (1) neural dynamics (1) model architecture (1) information geometry (1) neural response (1) recurrent neural network (1) data pruning (1) statistical mechanics (1) weight distribution (1) symmetry breaking (1) memory capacity (1) dataset selection (1) pattern formation (1) neural scaling law (1) dataset optimization (1) self-supervised metric (1) task-driven neural network (1) neuroscience modeling (1) self-supervised pruning (1)

Papers

A theory of weight distribution-constrained learning NeurIPS 2022 Beyond neural scaling laws: beating power law scaling via data pruning NeurIPS 2022 Explaining heterogeneity in medial entorhinal cortex with task-driven neural networks NeurIPS 2021 A unified theory for the origin of grid cells through the lens of pattern formation NeurIPS 2019