基本信息
浏览量:83
职业迁徙
个人简介
I am a Machine Learning PhD student at the University of Edinburgh, supervised by Prof. Amos Storkey. I am a member of the BayesWatch research group and the Adaptive and Neural Computation (ANC) research institute. My broader research topic is meta-learning in deep neural networks. More specifically, I am interested in applying meta-learning to learn a variety of internal network components (e.g. losses, optimizers, learning rates, architectures, memory modules, initializations etc.) such that a model can perform very well on a target task.
Wait.. What is meta-learning?
Meta-learning or learning to learn can be broadly defined as a machine learning paradigm, where we learn the learning algorithms themselves. The premise of such meta-learned learning algorithms lies in the fact that they are learned over a number of hours/days, and will often generalize better than manually invented learning algorithms. In essence, building systems that become more proficient at learning with more experience, thus learning how to learn.
Wait.. What is meta-learning?
Meta-learning or learning to learn can be broadly defined as a machine learning paradigm, where we learn the learning algorithms themselves. The premise of such meta-learned learning algorithms lies in the fact that they are learned over a number of hours/days, and will often generalize better than manually invented learning algorithms. In essence, building systems that become more proficient at learning with more experience, thus learning how to learn.
研究兴趣
论文共 19 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
Linus Ericsson, Miguel Espinosa,Chenhongyi Yang,Antreas Antoniou,Amos Storkey, Shay B. Cohen,Steven McDonagh,Elliot J. Crowley
CoRR (2024)
引用0浏览0EI引用
0
0
CoRR (2023)
引用0浏览0EI引用
0
0
arXiv (Cornell University) (2023)
semanticscholar(2019)
引用0浏览0引用
0
0
加载更多
作者统计
#Papers: 19
#Citation: 3678
H-Index: 7
G-Index: 19
Sociability: 4
Diversity: 0
Activity: 0
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