Demystifying Deep Learning in Predictive Spatio-Temporal Analytics: An Information-Theoretic Framework

no code implementations • 14 Sep 2020 • Qi Tan, Yang Liu, Jiming Liu

Deep learning has achieved incredible success over the past years, especially in various challenging predictive spatio-temporal analytics (PSTA) tasks, such as disease prediction, climate forecast, and traffic prediction, where intrinsic dependency relationships among data exist and generally manifest at multiple spatio-temporal scales.

Disease Prediction Traffic Prediction

Incremental training of multi-generative adversarial networks

no code implementations • ICLR 2019 • Qi Tan, Pingzhong Tang, Ke Xu, Weiran Shen, Song Zuo

Generative neural networks map a standard, possibly distribution to a complex high-dimensional distribution, which represents the real world data set.

Information-theoretic Multi-view Domain Adaptation

no code implementations • ACL 2012 • Pei Yang, Wei Gao, Qi Tan, Kam-Fai Wong

Document Classification Domain Adaptation +2