2022/11/13 by Daniel Hexner, Hexner, Daniel · 2 citations
Computer Science · Neuroscience · Physics and Astronomy · #FOS: Physical sciences #Neural Networks and Applications #Neural dynamics and brain function #Soft Condensed Matter (cond-mat.soft) #Theoretical and Computational Physics
paper · pdf · doi:10.48550/arxiv.2211.06893
openalex publication_date 2022/11/13 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
We introduce a training rule that enables a network composed of springs and dashpots to learn precise stress patterns. Our goal is to control the tensions on a fraction of "target" bonds, which are chosen randomly. The system is trained by applying stresses to the target bonds, causing the remaining bonds, which act as the learning degrees of freedom, to evolve. Different criteria for selecting the target bonds affects whether frustration is present. When there is at most a single target bond per node the error converges to computer precision. Additional targets on a single node may lead to slow convergence and failure. Nonetheless, training is successful even when approaching the limit predicted by the Maxwell Calladine theorem. We demonstrate the generality of these ideas by considering dashpots with yield stresses. We show that training converges, albeit with a slower, power-law decay of the error. Furthermore, dashpots with yielding stresses prevent the system from relaxing after training, enabling to encode permanent memories.