SCNO composes pre-trained spiking neural operator blocks for elementary PDE terms to solve unseen coupled PDEs with a frozen library plus a lightweight correction network, achieving lower error than monolithic baselines using only 95K parameters.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.LG 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
Synergistic active learning and input denoising reduces combined error in neural operators on viscous Burgers' equation from 15.42% to 2.04%, an 87% improvement over standard training.
citing papers explorer
-
SCNO: Spiking Compositional Neural Operator -- Towards a Neuromorphic Foundation Model for Nuclear PDE Solving
SCNO composes pre-trained spiking neural operator blocks for elementary PDE terms to solve unseen coupled PDEs with a frozen library plus a lightweight correction network, achieving lower error than monolithic baselines using only 95K parameters.
-
Beyond Uniform Sampling: Synergistic Active Learning and Input Denoising for Robust Neural Operators
Synergistic active learning and input denoising reduces combined error in neural operators on viscous Burgers' equation from 15.42% to 2.04%, an 87% improvement over standard training.