DynPMNNs replace static activations with time-evolving ODEs based on the FitzHugh-Nagumo model, achieve competitive regression performance on California Housing data with fewer parameters than Neural ODEs or CfCs, and are characterized as finite-dimensional solutions in RKBS.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Physics-Modeled Neural Networks
DynPMNNs replace static activations with time-evolving ODEs based on the FitzHugh-Nagumo model, achieve competitive regression performance on California Housing data with fewer parameters than Neural ODEs or CfCs, and are characterized as finite-dimensional solutions in RKBS.