AIConfPaper
← Search

Lukas Braun

4 accepted papers

2025

From Lazy to Rich: Exact Learning Dynamics in Deep Linear Networks

Clémentine Carla Juliette Dominé, Nicolas Anguita, Alexandra Maria Proca, Lukas Braun, Daniel Kunin, Pedro A. M. Mediano +1
ICLR 2025poster

Biological and artificial neural networks develop internal representations that enable them to perform complex tasks. In artificial networks, the effectiveness of these models relies on their ability to build task specific representation, a process influenced by interactions among datasets, architec…

Cited by 5Source ↗PDF ↗Scholar ↗
2025

Not all solutions are created equal: An analytical dissociation of functional and representational similarity in deep linear neural networks

Lukas Braun, Erin Grant, Andrew M Saxe
ICML 2025spotlight

A foundational principle of connectionism is that perception, action, and cognition emerge from parallel computations among simple, interconnected units that generate and rely on neural representations. Accordingly, researchers employ multivariate pattern analysis to decode and compare the neural co…

Cited by 0Source ↗PDF ↗Scholar ↗
2022

Exact learning dynamics of deep linear networks with prior knowledge

Lukas Braun, Clémentine Carla Juliette Dominé, James E Fitzgerald, Andrew M Saxe
NeurIPS 2022accept

Learning in deep neural networks is known to depend critically on the knowledge embedded in the initial network weights. However, few theoretical results have precisely linked prior knowledge to learning dynamics. Here we derive exact solutions to the dynamics of learning with rich prior knowledge i…

Cited by 42Source ↗PDF ↗Scholar ↗