Deep Learning and System Identification

被引：108

作者：

Ljung, Lennart ^{[1
]}

Andersson, Carl ^{[2
]}

Tiels, Koen ^{[3
]}

Schon, Thomas B. ^{[2
]}

机构：

[1] Linkoping Univ, Div Automat Control, Linkoping, Sweden

[2] Uppsala Univ, Dept Informat Technol, S-75105 Uppsala, Sweden

[3] Eindhoven Univ Technol, Dept Mech Engn, Eindhoven, Netherlands

来源：

IFAC PAPERSONLINE | 2020年 / 53卷 / 02期

基金：

瑞典研究理事会;

关键词：

Model structure; Bias/Variance Trade-off; Model Validation; LSTM; Cascadeforwardnet; Deep nets;

D O I：

10.1016/j.ifacol.2020.12.1329

中图分类号：

TP [自动化技术、计算机技术];

学科分类号：

0812 ;

摘要：

Deep learning is a topic of considerable interest today. Since it deals with estimating - or learning - models, there are connections to the area of System Identification developed in the Automatic Control community. Such connections are explored and exploited in this contribution. It is stressed that common deep nets such as feedforward and cascadeforward nets are nonlinear ARX (NARX) models, and can thus be easily incorporated in System Identification code and practice. The case of LSTM nets is an example of NonLinear State-Space (NLSS) models. Copyright (C) 2020 The Authors.

引用

页码：1175 / 1181

页数：7