565 citations · 838 across the 18 of their papers we have counts for
5 papers · 1 filter
Analog Physical Systems Can Exhibit Double Descent
Sam Dillavou, Jason W Rocks, Jacob F Wycoff +2
An important component of the success of large AI models is double descent, in which networks avoid overfitting as they grow relative to the amount of training data, instead improv…
Understanding and Embracing Imperfection in Physical Learning Networks
Sam Dillavou, Marcelo Guzman, Andrea J. Liu +1
Performing machine learning with analog signals offers advantages in speed and energy efficiency, but sensitivity to component and measurement imperfections often foils training wi…
Physical learning of power-efficient solutions
Menachem Stern, Sam Dillavou, Dinesh Jayaraman +2
As the size and ubiquity of artificial intelligence and computational machine learning (ML) models grow, their energy consumption for training and use is rapidly becoming economica…
Physical learning beyond the quasistatic limit
Menachem Stern, Sam Dillavou, Marc Z. Miskin +2
Physical networks, such as biological neural networks, can learn desired functions without a central processor, using local learning rules in space and time to learn in a fully dis…
Demonstration of Decentralized, Physics-Driven Learning
Sam Dillavou, Menachem Stern, Andrea J. Liu +1
In typical artificial neural networks, neurons adjust according to global calculations of a central processor, but in the brain neurons and synapses self-adjust based on local info…