[2603.23977] Kirchhoff-Inspired Neural Networks for Evolving High-Order Perception

Computer Science > Machine Learning arXiv:2603.23977 (cs) [Submitted on 25 Mar 2026] Title:Kirchhoff-Inspired Neural Networks for Evolving High-Order Perception Authors:Tongfei Chen, Jingying Yang, Linlin Yang, Jinhu Lü, David Doermann, Chunyu Xie, Long He, Tian Wang, Juan Zhang, Guodong Guo, Baochang Zhang View a PDF of the paper titled Kirchhoff-Inspired Neural Networks for Evolving High-Order Perception, by Tongfei Chen and 10 other authors View PDF HTML (experimental) Abstract:Deep learning architectures are fundamentally inspired by neuroscience, particularly the structure of the brain's sensory pathways, and have achieved remarkable success in learning informative data representations. Although these architectures mimic the communication mechanisms of biological neurons, their strategies for information encoding and transmission are fundamentally distinct. Biological systems depend on dynamic fluctuations in membrane potential; by contrast, conventional deep networks optimize weights and biases by adjusting the strengths of inter-neural connections, lacking a systematic mechanism to jointly characterize the interplay among signal intensity, coupling structure, and state evolution. To tackle this limitation, we propose the Kirchhoff-Inspired Neural Network (KINN), a state-variable-based network architecture constructed based on Kirchhoff's current law. KINN derives numerically stable state updates from fundamental ordinary differential equations, enabling the explicit...