Learning neural state-space models: do we need a state estimator?

06/26/2022
by   Marco Forgione, et al.
0

In recent years, several algorithms for system identification with neural state-space models have been introduced. Most of the proposed approaches are aimed at reducing the computational complexity of the learning problem, by splitting the optimization over short sub-sequences extracted from a longer training dataset. Different sequences are then processed simultaneously within a minibatch, taking advantage of modern parallel hardware for deep learning. An issue arising in these methods is the need to assign an initial state for each of the sub-sequences, which is required to run simulations and thus to evaluate the fitting loss. In this paper, we provide insights for calibration of neural state-space training algorithms based on extensive experimentation and analyses performed on two recognized system identification benchmarks. Particular focus is given to the choice and the role of the initial state estimation. We demonstrate that advanced initial state estimation techniques are really required to achieve high performance on certain classes of dynamical systems, while for asymptotically stable ones basic procedures such as zero or random initialization already yield competitive performance.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
12/14/2020

Nonlinear state-space identification using deep encoder networks

Nonlinear state-space identification for dynamical systems is most often...
research
04/13/2023

Neural State-Space Models: Empirical Evaluation of Uncertainty Quantification

Effective quantification of uncertainty is an essential and still missin...
research
04/04/2023

Initialization Approach for Nonlinear State-Space Identification via the Subspace Encoder Approach

The SUBNET neural network architecture has been developed to identify no...
research
11/26/2020

Physics-Informed Neural State Space Models via Learning and Evolution

Recent works exploring deep learning application to dynamical systems mo...
research
03/31/2020

Deep State Space Models for Nonlinear System Identification

An actively evolving model class for generative temporal models develope...
research
12/21/2017

Automatic Generation of Bounds for Polynomial Systems with Application to the Lorenz System

This study covers an analytical approach to calculate positively invaria...
research
04/20/2022

Deep subspace encoders for continuous-time state-space identification

Continuous-time (CT) models have shown an improved sample efficiency dur...

Please sign up or login with your details

Forgot password? Click here to reset