作者: Eric P. Xing , Xiaodan Liang , Zhiting Hu , Lianhui Qin , Zichao Yang
DOI:
关键词: Artificial intelligence 、 Generative grammar 、 Probabilistic logic 、 Domain knowledge 、 Reinforcement learning 、 Computer science 、 Regularization (mathematics)
摘要: The broad set of deep generative models (DGMs) has achieved remarkable advances. However, it is often difficult to incorporate rich structured domain knowledge with the end-to …