Deep autoencoders, and other deep neural networks, have demonstrated their effectiveness in discovering non-linear features across many problem domains. However, in many real-world problems, large outliers and pervasive noise are commonplace, and one may not have access to clean training data as required by standard deep denoising autoencoders. Herein, we demonstrate novel extensions to deep autoencoders which not only maintain a deep autoencoders' ability to discover high quality, non-linear features but can also eliminate outliers and noise without access to any clean training data. Our model is inspired by Robust Principal Component Analysis, and we split the input data X into two parts, $X = L_{D} + S$, where $L_{D}$ can be effectively reconstructed by a deep autoencoder and $S$ contains the outliers and noise in the original data X. Since such splitting increases the robustness of standard deep autoencoders, we name our model a "Robust Deep Autoencoder (RDA)". Further, we present generalizations of our results to grouped sparsity norms which allow one to distinguish random anomalies from other types of structured corruptions, such as a collection of features being corrupted across many instances or a collection of instances having more corruptions than their fellows. Such "Group Robust Deep Autoencoders (GRDA)" give rise to novel anomaly detection approaches whose superior performance we demonstrate on a selection of benchmark problems.

Anomaly Detection with Robust Deep Autoencoders

Lanthanide-based thermometers: At the cutting-edge of luminescence thermometry

In multiview learning, it is essential to assign a reasonable weight to each view according to the view importance. Thus, for multiview clustering task, a wise and elegant method should achieve clustering multiview data while learning the view weights. In this paper, we propose to explore a Laplacian rank constrained graph, which can be approximately as the centroid of the built graph for each view with different confidences. We start our work with a natural thought that the weights can be learned by introducing a hyperparameter. By analyzing the weakness of this way, we further propose a new multiview clustering method which is totally selfweighted. More importantly, once the target graph is obtained in our models, we can directly assign the cluster label to each data point and do not need any postprocessing such as K-means in standard spectral clustering. Evaluations on two synthetic datasets indicate the effectiveness of our methods. Compared with several representative graphbased multiview clustering approaches on four realworld datasets, the proposed methods achieve the better performances and our new clustering method is more practical to use.

Self-weighted Multiview Clustering with Multiple Graphs.

On 27 August 2016, the Juno spacecraft acquired science observations of Jupiter, passing less than 5000 kilometers above the equatorial cloud tops Images of Jupiter’s poles show a chaotic scene, unlike Saturn’s poles Microwave sounding reveals weather features at pressures deeper than 100 bars, dominated by an ammonia-rich, narrow low-latitude plume resembling a deeper, wider version of Earth’s Hadley cell Near-infrared mapping reveals the relative humidity within prominent downwelling regions Juno’s measured gravity field differs substantially from the last available estimate and is one order of magnitude more precise This has implications for the distribution of heavy elements in the interior, including the existence and mass of Jupiter’s core The observed magnetic field exhibits smaller spatial variations than expected, indicative of a rich harmonic content

https://science.sciencemag.org/content/sci/356/6340/821.full.pdf

Jupiter's interior and deep atmosphere: The initial pole-to-pole passes with the Juno spacecraft

Developing successful sign language recognition, generation, and translation systems requires expertise in a wide range of fields, including computer vision, computer graphics, natural language processing, human-computer interaction, linguistics, and Deaf culture. Despite the need for deep interdisciplinary knowledge, existing research occurs in separate disciplinary silos, and tackles separate portions of the sign language processing pipeline. This leads to three key questions: 1) What does an interdisciplinary view of the current landscape reveal? 2) What are the biggest challenges facing the field? and 3) What are the calls to action for people working in the field? To help answer these questions, we brought together a diverse group of experts for a two-day workshop. This paper presents the results of that interdisciplinary workshop, providing key background that is often overlooked by computer scientists, a review of the state-of-the-art, a set of pressing challenges, and a call to action for the research community.

https://dl.acm.org/doi/pdf/10.1145/3308561.3353774

蕭瓊瑞撰述

Papers

我的台灣, 看見心靈的故鄉 =2009林磐聳藝術與設計展