图 书 馆
常识智能：破解人工智能的长期挑战Commonsense Intelligence: Cracking the Longstanding Challenge in AI |
|
| 课程网址: | http://videolectures.net/www2021_choi_commonsense_intelligence/ |
| 主讲教师: | Yejin Choi |
| 开课单位: | 华盛顿大学 |
| 开课时间: | 2021-05-03 |
| 课程语种: | 英语 |
| 中文简介: |  |
| 课程简介: | Despite considerable advances in deep learning, AI remains to be narrow and brittle. One fundamental limitation is its lack of common sense: intuitive reasoning about everyday situations and events, which in turn, requires a wide spectrum of commonsense knowledge about how the physical and social world works, ranging from naive physics to folk psychology to ethical norms. In this talk, I will share our recent adventures in modeling neuro-symbolic commonsense models by melding symbolic and declarative knowledge stored in large-scale commonsense graphs with neural and implicit knowledge stored in large-scale neural language models. I will conclude the talk by discussing the needs for departing from the currently prevalent learning paradigms that lead to task- or even dataset-specific learning, and open research questions for commonsense AI in light of human cognition. |
| 关 键 词: | 人工智能; 常识模型建模; 大规模常识图 |
| 课程来源: | 视频讲座网 |
| 数据采集: | 2022-04-13：zkj |
| 最后编审: | 2022-04-13：zkj |
| 阅读次数: | 19 |