Neural Oscillators are Universal


METADATA ONLY
Loading...

Date

2023-05

Publication Type

Report

ETH Bibliography

yes

Citations

Altmetric
METADATA ONLY

Data

Rights / License

Abstract

Coupled oscillators are being increasingly used as the basis of machine learning (ML) architectures, for instance in sequence modeling, graph representation learning and in physical neural networks that are used in analog ML devices. We introduce an abstract class of neural oscillators that encompasses these architectures and prove that neural oscillators are universal, i.e, they can approximate any continuous and casual operator mapping between time-varying functions, to desired accuracy. This universality result provides theoretical justification for the use of oscillator based ML systems. The proof builds on a fundamental result of independent interest, which shows that a combination of forced harmonic oscillators with a nonlinear read-out suffices to approximate the underlying operators.

Publication status

published

Editor

Book title

Volume

2023-20

Pages / Article No.

Publisher

Seminar for Applied Mathematics, ETH Zurich

Event

Edition / version

Methods

Software

Geographic location

Date collected

Date created

Subject

Neural oscillators; Neural ODEs; Universal approximation; Deep learning; Hamiltonian systems

Organisational unit

03851 - Mishra, Siddhartha / Mishra, Siddhartha check_circle

Notes

Funding

770880 - Computation and analysis of statistical solutions of fluid flow (EC)

Related publications and datasets

Is previous version of: