- Open Access
Sequential learning and catastrophic forgetting in differentiable resistor networks
Phys. Rev. E 113, 065303 – Published 4 June, 2026
DOI: https://doi.org/10.1103/584w-2mxq
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 normalized 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 localized 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 test beds for studying continual learning in tunable matter.
Physics Subject Headings (PhySH)
Article Text
References (26)
- L. G. Wright, T. Onodera, M. M. Stein, T. Wang, D. T. Schachter, Z. Hu, and P. L. McMahon, Deep physical neural networks trained with backpropagation, Nature (London) 601, 549 (2022).
- A. Momeni, B. Rahmani, M. Malléjac, P. Del Hougne, and R. Fleury, Backpropagation-free training of deep physical neural networks, Science 382, 1297 (2023).
- A. Momeni et al., Training of physical neural networks, Nature (London) 645, 53 (2025).
- M. Stern and A. Murugan, Learning without neurons in physical systems, Annu. Rev. Condens. Matter Phys. 14, 417 (2023).
- M. Stern, D. Hexner, J. W. Rocks, and A. J. Liu, Supervised learning in physical networks: From machine learning to learning machines, Phys. Rev. X 11, 021045 (2021).
- M. Stern, M. Guzman, F. Martins, A. J. Liu, and V. Balasubramanian, Physical networks become what they learn, Phys. Rev. Lett. 134, 147402 (2025).
- M. Guzman, F. Martins, M. Stern, and A. J. Liu, Microscopic imprints of learned solutions in tunable networks, Phys. Rev. X 15, 031056 (2025).
- R. M. French, Catastrophic forgetting in connectionist networks, Trends Cognit. Sci. 3, 128 (1999).
- J. Kirkpatrick, R. Pascanu, N. Rabinowitz, J. Veness, G. Desjardins, A. A. Rusu, K. Milan, J. Quan, T. Ramalho, A. Grabska-Barwinska, et al., Overcoming catastrophic forgetting in neural networks, Proc. Natl. Acad. Sci. USA 114, 3521 (2017).
- F. Zenke, B. Poole, and S. Ganguli, Continual learning through synaptic intelligence, in Proceedings of the 34th International Conference on Machine Learning, edited by D. Precup and Y. W. Teh (PMLR, 2017), Vol. 70, pp. 3987–3995.
- J. Serra, D. Suris, M. Miron, and A. Karatzoglou, Overcoming catastrophic forgetting with hard attention to the task, in Proceedings of the 35th International Conference on Machine Learning, Stockholm, Sweden, edited by J. Dy and A. Krause (PMLR, 2018), Vol. 80, pp. 4548–4557.
- M. De Lange, R. Aljundi, M. Masana, S. Parisot, X. Jia, A. Leonardis, G. Slabaugh, and T. Tuytelaars, A continual learning survey Defying forgetting in classification tasks, IEEE Trans. Pattern Anal. Mach. Intell. 44, 3366 (2022).
- M. Davies et al., Loihi: A neuromorphic manycore processor with on-chip learning, IEEE Micro 38, 82 (2018).
- S. Furber, Large-scale neuromorphic computing systems, J. Neural Eng. 13, 051001 (2016).
- G. Indiveri and S.-C. Liu, Memory and information processing in neuromorphic systems, Proc. IEEE 103, 1379 (2025).
- S. Dillavou, B. D. Beyer, M. Stern, A. J. Liu, M. Z. Miskin, and D. J. Durian, Machine learning without a processor: Emergent learning in a nonlinear analog network, Proc. Natl. Acad. Sci. USA 121, e2319718121 (2024).
- M. Stern, S. Dillavou, D. Jayaraman, D. J. Durian, and A. J. Liu, Training self-learning circuits for power-efficient solutions, APL Machine Learning 2, 016114 (2024).
- P. Chatterjee, M. Guzman, and A. J. Liu, Remembrance of tasks past in tunable physical networks, arXiv:2512.03799.
- Z. Li and D. Hoiem, Learning without forgetting, IEEE Trans. Pattern Anal. Mach. Intell. 40, 2935 (2018).
- B. Scellier and Y. Bengio, Equilibrium propagation: Bridging the gap between energy-based models and backpropagation, Front. Comput. Neurosci. 11, 24 (2017).
- H. Jaeger and H. Haas, Harnessing nonlinearity: predicting chaotic systems and saving energy in wireless communication, Science 304, 78 (2004).
- G. Tanaka, T. Yamane, J. B. Héroux, R. Nakane, N. Kanazawa, S. Takeda, H. Numata, D. Nakano, and A. Hirose, Recent advances in physical reservoir computing: A review, Neural Networks 115, 100 (2019).
- S. Stepney, Physical reservoir computing: a tutorial, Nat. Comput. 23, 665 (2024).
- M. J. Falk, J. Wu, A. Matthews, V. Sachdeva, N. Pashine, M. L. Gardel, S. R. Nagel, and A. Murugan, Learning to learn by using nonequilibrium training protocols for adaptable materials, Proc. Natl. Acad. Sci. USA 120, e2219558120 (2023).
- S. Dillavou, M. Guzman, A. J. Liu, and D. J. Durian, Understanding and embracing imperfection in physical learning networks, arXiv:2505.22887.
- M. Ibrahim, Physical learning in resistor networks, version 1.0.0, Zenodo, 2026, https://doi.org/10.5281/zenodo.18909778; GitHub repository: https://github.com/Manirmaths/physical-learning-resistor-networks.
