Heng-Tze Cheng

Heng-Tze Cheng is a senior software engineer at Google Research. Heng-Tze has worked on Wide & Deep Learning in TensorFlow, as well as large-scale linear models and factorization machines with Sibyl. He has developed ranking and recommendation systems that are widely used across Google products. Prior to joining Google, Heng-Tze received his Ph.D. from Carnegie Mellon University in 2013 and B.S. from National Taiwan University in 2008. His research interests range across machine learning, information retrieval, user behavior modeling, and human activity recognition.

Google Publications

Previous Publications

  •   

    NuActiv: Recognizing Unseen New Activities Using Semantic Attribute-Based Learning

    Heng-Tze Cheng, Feng-Tso Sun, Martin Griss, Paul Davis, Jianguo Li, Di You

    Proceeding of the 11th Annual International Conference on Mobile Systems, Applications, and Services, ACM, New York, NY, USA (2013), pp. 361-374

  •   

    Towards zero-shot learning for human activity recognition using semantic attribute sequence model

    Heng-Tze Cheng, Martin Griss, Paul Davis, Jianguo Li, Di You

    UbiComp '13 Proceedings of the 2013 ACM international joint conference on Pervasive and ubiquitous computing, ACM