Control-oriented Denoising Autoencoder: Robustified Data-Driven Model Reduction. Issue 1 (July 2017)

• Record Type: Journal Article
• Authors: Nagasawa, Y.; Kashima, K.
• Is Part Of: IFAC-PapersOnLine. Volume 50:Issue 1(2017)
• Page Start: 2732
• Page End: 2737
• Publication Date: 2017-07
• Subjects: Model reduction -- statistical learning -- controllability analysis; Automatic control -- Periodicals; 629.805
• DOI: 10.1016/j.ifacol.2017.08.579
• Languages: English
• ISSNs: 2405-8963

Abstract

Abstract: Controllability quantification and model reduction of complex systems play an important role in many scientific and engineering fields. For this problem, the authors proposed a data-driven method based on statistical learning using neural networks, which we refer to as the control-oriented autoencoder . The important feature is that it is applicable to nonlinear systems, and that a suitable nonlinear projection can be given. For some systems, however, the method is excessively sensitive to computational error. In this paper, we analyze these phenomena from an over-fitting viewpoint, and enhance the robustness via denoising technique.