Premium
dynoNet : A neural network architecture for learning dynamical systems
Author(s) -
Forgione Marco,
Piga Dario
Publication year - 2021
Publication title -
international journal of adaptive control and signal processing
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.73
H-Index - 66
eISSN - 1099-1115
pISSN - 0890-6327
DOI - 10.1002/acs.3216
Subject(s) - differentiable function , linear dynamical system , dynamical systems theory , computer science , artificial neural network , sequence (biology) , identification (biology) , operator (biology) , dynamical system (definition) , backpropagation , artificial intelligence , deep learning , system identification , software , theoretical computer science , mathematics , data modeling , pure mathematics , software engineering , physics , repressor , chemistry , biology , genetics , biochemistry , quantum mechanics , transcription factor , programming language , botany , gene
Summary This article 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.