Stacked sparse denoising autoencoders (SSDAs) have recently been shown to be successful at removing noise from corrupted images. However, like most denoising techniques, the SSDA is not robust to variation in noise ty...
详细信息
Stacked sparse denoising autoencoders (SSDAs) have recently been shown to be successful at removing noise from corrupted images. However, like most denoising techniques, the SSDA is not robust to variation in noise types beyond what it has seen during training. To address this limitation, we present the adaptive multi-column stacked sparse denoising autoencoder (AMC-SSDA), a novel technique of combining multiple SSDAs by (1) computing optimal column weights via solving a nonlinear optimization program and (2) training a separate network to predict the optimal weights. We eliminate the need to determine the type of noise, let alone its statistics, at test time and even show that the system can be robust to noise not seen in the training set. We show that state-of-the-art denoising performance can be achieved with a single system on a variety of different noise types. Additionally, we demonstrate the efficacy of AMC-SSDA as a preprocessing (denoising) algorithm by achieving strong classification performance on corrupted MNIST digits.
Using tools from systems theory, it is now well known that classes of linear and nonlinear dynamic systems in firstorder form can be alternatively written in higher-order form, i.e., as sets of higher-order differenti...
详细信息
In this work, we find the optimal relay location for a secondary user in a cognitive radio network subject to outage constraints. With selection decode-and-forward relay protocol, we formulate this problem as a nonlin...
详细信息
Fringe projection profilometry technique has attracted more and more attention in the computer vision and found wide applications in the areas of high-precision measurement. This paper presents an accurate and robust ...
详细信息
Aeroservoelasticity, a multidisciplinary study of interactions between an active control system and the aeroelastic plant, has become very important with the advent of modem relaxed stability, flexible aircraft. Nonli...
详细信息
Dynamic non-linear models of the balance type are classified. Working with models is based on a combination of simulation and optimization methods. Optimization allows both quasi-dynamic and dynamic modes of operation...
详细信息
nonlinear programming (NLP) is a field in mathematics that focuses on iteratively decreasing an arbitrary cost function. In this paper, a NLP approach based on extremum seeking control (ESC) is modified for the purpos...
详细信息
Historical evolution of engineering disciplines and the complexity of the MDO problem suggest that disciplinary autonomy is a desirable goal in formulating and solving MDO problems. We examine the notion of disciplina...
详细信息
作者：
Deng, Tian-BoFaculty of Science
Toho University Department of Information Science Miyama 2-2-1 Funabashi Chiba274-8510 Japan
Since implementing a high-order digital system using low-order systems has many advantages such as low coefficient-quantization sensitivity and high implementation modularity, this paper formulates the optimal design ...
详细信息
暂无评论