Deep neural network based adaptive learning for switched systems

07/11/2022
by   Junjie He, et al.
0

In this paper, we present a deep neural network based adaptive learning (DNN-AL) approach for switched systems. Currently, deep neural network based methods are actively developed for learning governing equations in unknown dynamic systems, but their efficiency can degenerate for switching systems, where structural changes exist at discrete time instants. In this new DNN-AL strategy, observed datasets are adaptively decomposed into subsets, such that no structural changes within each subset. During the adaptive procedures, DNNs are hierarchically constructed, and unknown switching time instants are gradually identified. Especially, network parameters at previous iteration steps are reused to initialize networks for the later iteration steps, which gives efficient training procedures for the DNNs. For the DNNs obtained through our DNN-AL, bounds of the prediction error are established. Numerical studies are conducted to demonstrate the efficiency of DNN-AL.

READ FULL TEXT
research
04/02/2019

A comparative study of physics-informed neural network models for learning unknown dynamics and constitutive relations

We investigate the use of discrete and continuous versions of physics-in...
research
06/29/2021

NEUKONFIG: Reducing Edge Service Downtime When Repartitioning DNNs

Deep Neural Networks (DNNs) may be partitioned across the edge and the c...
research
01/25/2021

CPT: Efficient Deep Neural Network Training via Cyclic Precision

Low-precision deep neural network (DNN) training has gained tremendous a...
research
02/19/2020

Implicit bias with Ritz-Galerkin method in understanding deep learning for solving PDEs

This paper aims at studying the difference between Ritz-Galerkin (R-G) m...
research
11/27/2022

A Self-adaptive Neuroevolution Approach to Constructing Deep Neural Network Architectures Across Different Types

Neuroevolution has greatly promoted Deep Neural Network (DNN) architectu...
research
06/14/2021

Deep neural networks for geometric multigrid methods

We investigate scaling and efficiency of the deep neural network multigr...
research
11/23/2017

DNN-Buddies: A Deep Neural Network-Based Estimation Metric for the Jigsaw Puzzle Problem

This paper introduces the first deep neural network-based estimation met...

Please sign up or login with your details

Forgot password? Click here to reset