Abstract:Differentiable physical networks provide a simple setting in which learning can be studied through the interaction between trainable parameters and physical equilibrium constraints. We investigate sequential learning in differentiable resistor networks governed by Kirchhoff's laws. Although individual input--output mappings can be learned by gradient-based adjustment of edge conductances, sequential training on conflicting tasks produces catastrophic forgetting. We show that forgetting is controlled by task conflict and by the degree of adaptation to the new task. Uniform anchoring and normalised gradient-weighted anchoring reduce forgetting only by increasing the final loss on the new task, giving a clear forgetting--adaptation trade-off. We also show that forgetting is associated with localised conductance changes on high-current edges, giving a physical interpretation as reconfiguration of dominant transport pathways. Broader random-task ensembles show that the strongest forgetting occurs when the second task reverses the output ordering imposed by the first task. Finally, comparisons across Erdős--Rényi, small-world, scale-free, and random-geometric graph ensembles show that topology changes the forgetting--adaptation balance. These results position differentiable resistor networks as compact, physically interpretable testbeds for studying continual learning in tunable matter.
| Subjects: | Machine Learning (cs.LG); Disordered Systems and Neural Networks (cond-mat.dis-nn); Computational Physics (physics.comp-ph) |
| MSC classes: | 68T07, 05C82 |
| Cite as: | arXiv:2605.01383 [cs.LG] |
| (or arXiv:2605.01383v1 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2605.01383 arXiv-issued DOI via DataCite (pending registration) |
From: Maniru Ibrahim [view email]
[v1]
Sat, 2 May 2026 11:15:57 UTC (1,004 KB)
此内容由惯性聚合(RSS阅读器)自动聚合整理，仅供阅读参考。 原文来自 — 版权归原作者所有。