Coupled Oscillatory Recurrent Neural Network (coRNN): An accurate and (gradient) stable architecture for learning long time dependencies

Siddhartha Mishra; T. Konstantin Rusch

Coupled Oscillatory Recurrent Neural Network (coRNN): An accurate and (gradient) stable architecture for learning long time dependencies

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2010.00951 v2 pith:SU7Z3RF7 submitted 2020-10-02 cs.LG cs.NEstat.ML

Coupled Oscillatory Recurrent Neural Network (coRNN): An accurate and (gradient) stable architecture for learning long time dependencies

T. Konstantin Rusch , Siddhartha Mishra This is my paper

classification cs.LG cs.NEstat.ML

keywords architecturenetworksaccuratecoupledgradientgradientsneuraloscillators

verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved

0 comments

read the original abstract

Circuits of biological neurons, such as in the functional parts of the brain can be modeled as networks of coupled oscillators. Inspired by the ability of these systems to express a rich set of outputs while keeping (gradients of) state variables bounded, we propose a novel architecture for recurrent neural networks. Our proposed RNN is based on a time-discretization of a system of second-order ordinary differential equations, modeling networks of controlled nonlinear oscillators. We prove precise bounds on the gradients of the hidden states, leading to the mitigation of the exploding and vanishing gradient problem for this RNN. Experiments show that the proposed RNN is comparable in performance to the state of the art on a variety of benchmarks, demonstrating the potential of this architecture to provide stable and accurate RNNs for processing complex sequential data.

discussion (0)

Forward citations

Cited by 3 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

CWRNN-INVR: A Coupled WarpRNN based Implicit Neural Video Representation
eess.IV 2026-04 unverdicted novelty 6.0

CWRNN-INVR combines WarpRNN for structured video information and residual grids for irregular details to reach 33.73 dB average PSNR on the UVG dataset at 3M parameters, outperforming existing INVR methods.
Upper Generalization Bounds for Neural Oscillators
cs.LG 2026-03 conditional novelty 6.0

Upper generalization bounds for neural oscillators scale polynomially with MLP size and time length, avoiding the curse of parametric complexity, with numerical validation on a Bouc-Wen nonlinear system.
Upper Approximation Bounds for Neural Oscillators
cs.LG 2025-11 unverdicted novelty 5.0

Upper bounds are derived showing that neural oscillator approximation errors for causal operators and stable second-order dynamical systems scale polynomially with the reciprocals of the widths of the two MLPs.