activity
20242026
collaborators

5 papers

cond-mat.dis-nn2026

Contrastive learning in tunable dynamical systems

Menachem Stern, Adam G. Frim, Raúl Candás +2

We generalize the theory of supervised contrastive learning, previously applied to physical systems at equilibrium or steady state, to systems following any dynamics described by c…

cond-mat.dis-nn2026

Learning Associations in Reconfigurable Particle Packings via Local Cyclic Driving

Wenjing Guo, Vidyesh Rao Anisetti, Kairui Zhang +7

We investigate associative-memory behavior in a reconfigurable particle packing programmed by purely local cyclic driving. The system is a two-dimensional bidisperse Lennard--Jones…

cs.LG2025

Harnessing intuitive local evolution rules for physical learning

Roie Ezraty, Menachem Stern, Shmuel M. Rubinstein

Machine Learning, however popular and accessible, is computationally intensive and highly power-consuming, prompting interest in alternative physical implementations of learning ta…

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…