글번호
77171643
일 자
24.03.18
조회수
380
글쓴이
ims
[2024.03.19] Barron space for Barron space for Graph Convolution Neural Networks

■ 연사: Qiyu Sun (Department of Mathematics, University of Central Florida, USA) 

■ 제목: Barron space for Barron space for Graph Convolution Neural Networks

■ 일시: 2024년 3월 19일(화) 17:00

■ 장소: 종합과학관 A동 317호

■ 초록:  In this talk, we introduce a Barron space of functions on a compact domain of graph signals, discuss its various properties, such as reproducing kernel Banach space property and universal approximation property. We will also discuss well approximation property of functions in the Barron space by outputs of some  graph convolution neural networks, and learnability of functions in the Barron space from their random samples. 

■ 문의: (02)3277-6990/ims@ewha.ac.kr

다음글 [2024.06.07] Yonsei Ewha Sogang Seminar on Analysis & PDEs
이전글 EIMS Recruitment Announcement for Research Professors and Postdoctoral Researchers