Control-oriented Denoising Autoencoder: Robustified Data-Driven Model Reduction
نویسندگان
چکیده
منابع مشابه
Denoising without access to clean data using a partitioned autoencoder
Training a denoising autoencoder neural network requires access to truly clean data, a requirement which is often impractical. To remedy this, we introduce a method to train an autoencoder using only noisy data, having examples with and without the signal class of interest. The autoencoder learns a partitioned representation of signal and noise, learning to reconstruct each separately. We illus...
متن کاملAn object-oriented data-driven migration model.
This research uses object-oriented simulation to derive the migratory patterns of animal populations. These patterns are then compared with the trajectories of aquatic pollutant releases to yield quantitative biological impact assessments. These estimates are more realistic than those based on assumptions of uniform or random distributions of animals in a region--a common approach to this probl...
متن کاملControl-Oriented Model Reduction for Parabolic Systems
In the present work, the efficient implementation of model order reduction methods for linear, time-invariant control systems is investigated. Model reduction is common in simulation, control and optimization of complex dynamical systems arising in modeling of physical processes and in the spatial discretization of parabolic partial differential equations (PDEs) in three or more dimensions. If ...
متن کاملReverberant speech recognition based on denoising autoencoder
Denoising autoencoder is applied to reverberant speech recognition as a noise robust front-end to reconstruct clean speech spectrum from noisy input. In order to capture context effects of speech sounds, a window of multiple short-windowed spectral frames are concatenated to form a single input vector. Additionally, a combination of short and long-term spectra is investigated to properly handle...
متن کاملA Denoising Autoencoder that Guides Stochastic Search
An algorithm is described that adaptively learns a non-linear mutation distribution. It works by training a denoising autoencoder (DA) online at each generation of a genetic algorithm to reconstruct a slowly decaying memory of the best genotypes so far. A compressed hidden layer forces the autoencoder to learn hidden features in the training set that can be used to accelerate search on novel pr...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: IFAC-PapersOnLine
سال: 2017
ISSN: 2405-8963
DOI: 10.1016/j.ifacol.2017.08.579