AI RESEARCH
Upper Approximation Bounds for Neural Oscillators
arXiv CS.LG
•
ArXi:2512.01015v2 Announce Type: replace Neural oscillators, originating from second-order ordinary differential equations (ODEs), have nstrated strong performance in stably learning causal mappings between long-term sequences or continuous temporal functions, as well as in accurately approximating physical systems. However, theoretically quantifying the capacities of their neural network architectures remains a significant challenge. In this study, the neural oscillator consisting of a second-order ODE followed by a multilayer perceptron (MLP) is considered.