<i>dynoNet</i>: A neural network architecture for learning dynamical systems
Marco Forgione, Dario Piga
Abstract
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.
Topics & Concepts
Differentiable functionLinear dynamical systemDynamical systems theoryComputer scienceArtificial neural networkSequence (biology)Identification (biology)Operator (biology)Dynamical system (definition)BackpropagationArtificial intelligenceDeep learningSystem identificationSoftwareTheoretical computer scienceMathematicsData modelingPure mathematicsSoftware engineeringPhysicsTranscription factorProgramming languageGeneticsGeneRepressorBiologyQuantum mechanicsBotanyBiochemistryChemistryNeural Networks and ApplicationsControl Systems and IdentificationModel Reduction and Neural Networks