Deep neural networks (DNNs) have achieved state-of-the-art results on time series
classification (TSC) tasks. In this work, we focus on leveraging DNNs in the often …

Time-series forecasting is important for many applications. Forecasting models are usually
trained using time-series data in a specific target task. However, sufficient data in the target …

Topic models have been successfully used for analyzing text documents. However, with
existing topic models, many documents are required for training. In this paper, we propose a …

Neural network-based anomaly detection methods have shown to achieve high
performance. However, they require a large amount of training data for each task. We …

Meta-learning is an important approach to improve machine learning performance with a
limited number of observations for target tasks. However, when observations are …

The fast evolution of mobile internet and remote sensing technologies has facilitated the
generation and collection of numerous time-series data from the real-world systems, which …

Labelling can suffer from annoying problems, such as expensive costs, unavailability, users'
privacy violation, and low-quality labels. With only limited labelled samples, how to learn a …

Compilation is the process of translating the textual representation of source code into
machine code. This process is traditionally implemented as a series of single-threaded …