基本信息
浏览量:1103
职业迁徙
个人简介
I am generally interested in Representation Learning, Generative Modeling and Generalizable Reinforcement Learning. Specifically, my current research focuses on learning generative models and/or representation functions such that the resulted coding can recover various factors of variation in our highly structured world, so as to emerge the cognition of "semantic meanings". A representation that successfully matches such a requirement is expected to exhibit systematicity and generalizability:
Being systematic in the sense of being sparsely distributed in a low-dimensional manifold, where the vector coding is equivariant to the transformation for each factor of variation and invariant to other irrelevant factors;
Being generalizable in the sense of productively composing/correlating intuitively independent factors to extrapolate beyond training domains, and gracefully preserving causal invariance under distribution shifts.
The hope is that with such representations, artificial agents can understand novel contexts, imagine unseen situations, and design causal interventions, all at the abstract level, hence efficiently plan for intelligent strategies. I draw inspiration broadly from classical AI, cognitive science, computational neuroscience, statistical modeling, and causality. Previously, I worked on (inverse) reinforcement learning and evolving architectures of representation functions (a.k.a. Differentiable Neural Architecture Search).
研究兴趣
论文共 17 篇作者统计合作学者相似作者
按年份排序按引用量排序主题筛选期刊级别筛选合作者筛选合作机构筛选
时间
引用量
主题
期刊级别
合作者
合作机构
Deqian Kong, Dehong Xu, Minglu Zhao,Bo Pang,Jianwen Xie,Andrew Lizarraga, Yuhao Huang,Sirui Xie,Ying Nian Wu
CoRR (2024)
引用0浏览0EI引用
0
0
NeurIPS (2023)
引用1浏览0EI引用
1
0
加载更多
作者统计
合作学者
合作机构
D-Core
- 合作者
- 学生
- 导师
数据免责声明
页面数据均来自互联网公开来源、合作出版商和通过AI技术自动分析结果,我们不对页面数据的有效性、准确性、正确性、可靠性、完整性和及时性做出任何承诺和保证。若有疑问,可以通过电子邮件方式联系我们:report@aminer.cn