activity
20242026
collaborators

5 papers

cond-mat.dis-nn2026

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…

cond-mat.dis-nn2025

Remembrance of Tasks Past in Tunable Physical Networks

Purba Chatterjee, Marcelo Guzman, Andrea J. Liu

Sequential learning in physical networks is hindered by catastrophic forgetting, where training a new task erases solutions to earlier ones. We show that we can significantly enhan…

cond-mat.dis-nn2025

Unsupervised and probabilistic learning with Contrastive Local Learning Networks: The Restricted Kirchhoff Machine

Marcelo Guzman, Simone Ciarella, Andrea J. Liu

Autonomous physical learning systems modify their internal parameters and solve computational tasks without relying on external computation. Compared to traditional computers, they…

cond-mat.dis-nn2025

Physical networks become what they learn

Menachem Stern, Marcelo Guzman, Felipe Martins +2

Physical networks can develop diverse responses, or functions, by design, evolution or learning. We focus on electrical networks of nodes connected by resistive edges. Such network…

cond-mat.dis-nn2024

Microscopic imprints of learned solutions in adaptive resistor networks

Marcel Guzman, Felipe Martins, Menachem Stern +1

In physical networks trained using supervised learning, physical parameters are adjusted to produce desired responses to inputs. An example is electrical contrastive local learning…