Related papers: DCSF: Deep Convolutional Set Functions for Classif…
Asynchronous methods are widely used in deep learning, but have limited theoretical justification when applied to non-convex problems. We show that running stochastic gradient descent (SGD) in an asynchronous manner can be viewed as adding…
Multivariate time series (MTS) analysis prevails in real-world applications such as finance, climate science and healthcare. The various self-attention mechanisms, the backbone of the state-of-the-art Transformer-based models, efficiently…
Time series motifs play an important role in the time series analysis. The motif-based time series clustering is used for the discovery of higher-order patterns or structures in time series data. Inspired by the convolutional neural network…
Time series data analysis is a critical component in various domains such as finance, healthcare, and meteorology. Despite the progress in deep learning for time series analysis, there remains a challenge in addressing the non-stationary…
Time series forecasting (TSF) is critical across domains such as finance, meteorology, and energy. While extending the lookback window theoretically provides richer historical context, in practice, it often introduces irrelevant noise and…
Fully convolutional neural networks (FCN) have been shown to achieve state-of-the-art performance on the task of classifying time series sequences. We propose the augmentation of fully convolutional networks with long short term memory…
We propose Significance-Offset Convolutional Neural Network, a deep convolutional network architecture for regression of multivariate asynchronous time series. The model is inspired by standard autoregressive (AR) models and gating…
Deep learning models utilizing convolution layers have achieved state-of-the-art performance on univariate time series classification tasks. In this work, we propose improving CNN based time series classifiers by utilizing Octave…
The emergence of deep learning has yielded noteworthy advancements in time series forecasting (TSF). Transformer architectures, in particular, have witnessed broad utilization and adoption in TSF tasks. Transformers have proven to be the…
Nowadays, multivariate time series data are increasingly collected in various real world systems, e.g., power plants, wearable devices, etc. Anomaly detection and diagnosis in multivariate time series refer to identifying abnormal status in…
With several new large-scale surveys on the horizon, including LSST, TESS, ZTF, and Evryscope, faster and more accurate analysis methods will be required to adequately process the enormous amount of data produced. Deep learning, used in…
Aiming at improving performance of visual classification in a cost-effective manner, this paper proposes an incremental semi-supervised learning paradigm called Deep Co-Space (DCS). Unlike many conventional semi-supervised learning methods…
Time series anomaly detection has applications in a wide range of research fields and applications, including manufacturing and healthcare. The presence of anomalies can indicate novel or unexpected events, such as production faults, system…
As a crucial component in intelligent transportation systems, traffic flow prediction has recently attracted widespread research interest in the field of artificial intelligence (AI) with the increasing availability of massive traffic…
Time series analysis plays a vital role in fields such as finance, healthcare, industry, and meteorology, underpinning key tasks including classification, forecasting, and anomaly detection. Although deep learning models have achieved…
One of the most important steps toward interpretability and explainability of neural network models is feature selection, which aims to identify the subset of relevant features. Theoretical results in the field have mostly focused on the…
Time series forecasting has widespread applications in urban life ranging from air quality monitoring to traffic analysis. However, accurate time series forecasting is challenging because real-world time series suffer from the distribution…
Two fundamental problems in unsupervised learning are efficient inference for latent-variable models and robust density estimation based on large amounts of unlabeled data. Algorithms for the two tasks, such as normalizing flows and…
Multitask learning (MTL) aims to develop a unified model that can handle a set of closely related tasks simultaneously. By optimizing the model across multiple tasks, MTL generally surpasses its non-MTL counterparts in terms of…
Dataset condensation is a newborn technique that generates a small dataset that can be used in training deep neural networks to lower training costs. The objective of dataset condensation is to ensure that the model trained with the…