W
Wei-Cheng Chang
Researcher at Carnegie Mellon University
Publications - 22
Citations - 2536
Wei-Cheng Chang is an academic researcher from Carnegie Mellon University. The author has contributed to research in topics: Computer science & Deep learning. The author has an hindex of 10, co-authored 15 publications receiving 1648 citations. Previous affiliations of Wei-Cheng Chang include National Taiwan University.
Papers
More filters
Proceedings ArticleDOI
Modeling Long- and Short-Term Temporal Patterns with Deep Neural Networks
TL;DR: A novel deep learning framework, namely Long- and Short-term Time-series network (LSTNet), to address this open challenge of multivariate time series forecasting, using the Convolution Neural Network and the Recurrent Neural Network to extract short-term local dependency patterns among variables and to discover long-term patterns for time series trends.
Proceedings ArticleDOI
Deep Learning for Extreme Multi-label Text Classification
TL;DR: This paper presents the first attempt at applying deep learning to XMTC, with a family of new Convolutional Neural Network models which are tailored for multi-label classification in particular.
Proceedings Article
MMD GAN: Towards Deeper Understanding of Moment Matching Network
TL;DR: In the evaluation on multiple benchmark datasets, including MNIST, CIFAR- 10, CelebA and LSUN, the performance of MMD-GAN significantly outperforms GMMN, and is competitive with other representative GAN works.
Posted Content
MMD GAN: Towards Deeper Understanding of Moment Matching Network
TL;DR: MMD GAN as discussed by the authors improves both the model expressiveness of GMMN and its computational efficiency by introducing adversarial kernel learning techniques, as the replacement of a fixed Gaussian kernel in the original GMMN.
Posted Content
Modeling Long- and Short-Term Temporal Patterns with Deep Neural Networks
TL;DR: Long and Short-term Time-series Network (LSTNet) as mentioned in this paper uses CNN and RNN to extract short-term local dependency patterns among variables and to discover long-term patterns for time series trends.