The Neural Race Reduction: Dynamics of Abstraction in Gated Networks

The Neural Race Reduction: Dynamics of Abstraction in Gated Networks

21 July 2022

Papers citing "The Neural Race Reduction: Dynamics of Abstraction in Gated Networks"

11 / 11 papers shown

Title
Memorization and Knowledge Injection in Gated LLMs Xu Pan Ely Hahami Zechen Zhang H. Sompolinsky KELM CLL RALM 104 0 0 30 Apr 2025
Make Haste Slowly: A Theory of Emergent Structured Mixed Selectivity in Feature Learning ReLU Networks Devon Jarvis Richard Klein Benjamin Rosman Andrew M. Saxe MLT 64 1 0 08 Mar 2025
Strategy Coopetition Explains the Emergence and Transience of In-Context Learning Aaditya K. Singh Ted Moskovitz Sara Dragutinovic Felix Hill Stephanie C. Y. Chan Andrew Saxe 115 0 0 07 Mar 2025
Flexible task abstractions emerge in linear networks with fast and bounded units Kai Sandbrink Jan P. Bauer A. Proca Andrew M. Saxe Christopher Summerfield Ali Hummos 58 2 0 17 Jan 2025
When does compositional structure yield compositional generalization? A kernel theory Samuel Lippl Kim Stachenfeld NAI CoGe 65 5 0 26 May 2024
Critical Learning Periods Emerge Even in Deep Linear Networks Michael Kleinman Alessandro Achille Stefano Soatto 34 3 0 23 Aug 2023
Globally Gated Deep Linear Networks Qianyi Li H. Sompolinsky AI4CE 9 9 0 31 Oct 2022
Continual task learning in natural and artificial agents Timo Flesch Andrew M. Saxe Christopher Summerfield CLL 35 24 0 10 Oct 2022
Deep Neural Networks as Complex Networks Emanuele La Malfa G. Malfa Claudio Caprioli Giuseppe Nicosia Vito Latora PINN GNN 29 4 0 12 Sep 2022
Omnivore: A Single Model for Many Visual Modalities Rohit Girdhar Mannat Singh Nikhil Ravi L. V. D. van der Maaten Armand Joulin Ishan Misra 211 225 0 20 Jan 2022
Characterizing Learning Dynamics of Deep Neural Networks via Complex Networks Emanuele La Malfa G. Malfa Giuseppe Nicosia Vito Latora 19 10 0 06 Oct 2021