dynoNet: a neural network architecture for learning dynamical systems

Marco Forgione, Dario Piga
6/3/2020
cs.LGeess.SYstat.ML

Official code: forgi86/dynonet (49 stars, MIT, PyTorch, last commit 2024-05-31).

Abstract

This paper introduces a network architecture, called dynoNet, utilizing linear dynamical operators as elementary building blocks. Owing to the dynamical nature of these blocks, dynoNet networks are tailored for sequence modeling and system identification purposes. The back-propagation behavior of the linear dynamical operator with respect to both its parameters and its input sequence is defined. This enables end-to-end training of structured networks containing linear dynamical operators and other differentiable units, exploiting existing deep learning software. Examples show the effectiveness of the proposed approach on well-known system identification benchmarks. Examples show the effectiveness of the proposed approach against well-known system identification benchmarks.

View on arXivView PDF

Code Implementations(1)

forgi86/dynonetOfficial100%
PyTorchMIT

"dynoNet: A neural network architecture for learning dynamical systems" by Marco Forgione and Dario Piga

4914Python, MakefileMar 21, 20202 years agoMIT
deep-learningdifferentiable-transfer-functionslinear-dynamical-operatorspytorch

Similar Papers

LeARN: Learnable and Adaptive Representations for Nonlinear Dynamics in System Identification

86% match2024

Systematic construction of continuous-time neural networks for linear dynamical systems

84% match2024

A Mathematical Guide to Operator Learning

83% match2023

Constants of motion network revisited

83% match2025

Structure Over Nonlinearity: Explicit Interaction Architectures for Dynamical Learning

83% match2026

Structural Inference of Networked Dynamical Systems with Universal Differential Equations

83% match2022

Cite this paper

@article{forgione2020dynonet,
  title  = {dynoNet: a neural network architecture for learning dynamical systems},
  author = {Marco Forgione and Dario Piga},
  year   = {2020},
  eprint = {2006.02250},
  archivePrefix = {arXiv},
  url    = {https://arxiv.org/abs/2006.02250}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2006.02250.svg)](https://codeofpaper.com/paper/2006.02250)

Discussion