基本信息
浏览量:24
职业迁徙
个人简介
As someone who has a deep fascination for the abstract concepts of mathematics and a strong drive to create tangible impact in the world, I strive for a balanced approach in my research. My focus revolves around bridging the gap between abstract ideas and tangible applications of machine learning. This dual approach has led me to explore the applications of machine learning in robotics, NLP, and knowledge graphs, while also nurturing my passion for foundational aspects of machine learning such as representation learning. While most representation learning methods only focus on metric learning, my work on box embeddings aims to show that representation learning can also capture various other kinds of structures like algebraic and relational structure, thereby allowing models to perform compositional reasoning. I believe that learning objectives and uncertainty quantification methods based solely on probability are restrictive. As a result, I have explored energy models, where the objective is to use energy model as a learned loss function to train a feedforward prediction network. Various frameworks quantifying uncertainty have been proposed over the years. However, none of these frameworks are suited to measure the uncertainty in modern deep learning models like transformers. My current research focuses on creating novel methods to model uncertainty in transformer-based models. I am also interested in analyzing the limits of compositional generalization achievable through in-context learning with transformers, approaching it from the perspective of minimum description length and compression.
研究兴趣
论文共 14 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
arxiv(2024)
引用0浏览0引用
0
0
引用7浏览0EI引用
7
0
ClinicalNLP@EMNLP (2020): 178-193
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