开课单位--马萨诸塞大学阿默斯特分校
1 1/1

1
Representation and Reasoning with Universal Schema Embeddings[通用模式嵌入的表示与推理]
  Andrew McCallum(马萨诸塞大学阿默斯特分校) Work in knowledge representation has long struggled to design schemas of entity- and relation-types that capture the desired balance of specificity an...
热度：30

2
WattHome: A Data‑driven Approach for Energy Efficiency Analytics at City‑scale[WattHome：城市级能效分析的数据驱动方法]
  Srinivasan Iyengar(马萨诸塞大学阿默斯特分校) WattHome: A Data‑driven Approach for Energy Efficiency Analytics at City‑scale
热度：40

3
Building Nearline Contextual Recommendations for Active Communities on LinkedIn[在LinkedIn上为活跃社区构建近线上下文建议]
  Hema Raghavan(马萨诸塞大学阿默斯特分校) At LinkedIn our mission is to use AI to connect every member of the global workforce to make them more productive and successful. The social network i...
热度：23

4
Naranjo Question Answering using End-to-End Multi-task Learning Model[使用端到端多任务学习模型的Naranjo问答]
  Bhanu Pratap Singh Rawat(马萨诸塞大学阿默斯特分校) In the clinical domain, it is important to understand whether an adverse drug reaction (ADR) is caused by a particular medication. Clinical judgement ...
热度：34

5
Proximal Reinforcement Learning: Learning to Act in Primal Dual Spaces[近端强化学习：学习在原始-对偶空间中行动]
  Sridhar Mahadevan(马萨诸塞大学阿默斯特分校) In this talk, we set forth a new framework for reinforcement learning developed by us over the past few years, one that yields mathematically rigorous...
热度：76
1 1/1