… of learning discriminative features (segments) from both labeled and unlabeled time series
… SSSL with other shapelet learning models using advanced time series representation and …

… We propose U-Time, a fully feed-forward deep learning approach to physiological time
series segmentation developed for the analysis of sleep data. U-Time is a temporal fully …

… deep learning efforts related to time series anomaly detection were based on recurrent neural
networks (RNN). In this paper, we propose a time series … for time series segmentation as …

… a deep learning-based automatic way to segment the glioma, which is called brain tumor
segmentation (… With the rapid development of the deep learning technique, deep convolutional …

… the temporal context, and set anomaly criteria. Through Section VI-A to VI-B, we evaluate the
deep learning… patterns in segmented time series. Hence, one of its drawbacks is that it is not …

… ) and temporal dependencies (RNNs). In this work, we propose the first deep learning architecture
… For this reason, we propose a deep learning architecture for the analysis of SITS data, …

… To make the training effective, we apply DSN to facilitate the feature learning of each … a
deep hierarchical features learning architecture, named DeepCrack, for crack segmentation, …

… temporal dynamics among conseutive time steps of the sensor data. This deep learning
approach can successfully obviate the need for manual data segmentation and feature …

… one neural network topology using gradient backpropagation. … three deep learning mechanisms
on four deep learning … to clouds) or the number of segments (model complexity). These …

… To address this, this paper extends preliminary experiments of a novel deep learning–based
method that will allow the automatic discovery of intricate structures in sensor signals that …