https://www.math.snu.ac.kr/board/files/attach/images/701/ff97c54e6e21a4ae39315f9a12b27314.png
Extra Form
Lecturer 신연종
Dept. KAIST
date Oct 13, 2022

 

Machine learning (ML) has achieved unprecedented empirical success in diverse applications. It now has been applied to solve scientific problems, which has become an emerging field, Scientific Machine Learning (SciML). Many ML techniques, however, are very complex and sophisticated, commonly requiring many trial-and-error and tricks. These result in a lack of robustness and interpretability, which are critical factors for scientific applications. This talk centers around mathematical approaches for SciML, promoting trustworthiness. The first part is about how to embed physics into neural networks (NNs). I will present a general framework for designing NNs that obey the first and second laws of thermodynamics. The framework not only provides flexible ways of leveraging available physics information but also results in expressive NN architectures. The second part is about the training of NNs, one of the biggest challenges in ML. I will present an efficient training method for NNs - Active Neuron Least Squares (ANLS). ANLS is developed from the insight gained from the analysis of gradient descent training.

Atachment
Attachment '1'
List of Articles
Category Subject Dept. Lecturer
Math Colloquia <학부생을 위한 ɛ 강연> Introduction to the incompressible Navier-Stokes equations file UNIST 배한택
Math Colloquia Essential dimension of simple algebras file KAIST 백상훈
Math Colloquia 1 is big enough to understand 3 file 카이스트 백형렬
Math Colloquia 학부생을 위한 강연: Introduction to partial differential equations file 서울대학교 변순식
Math Colloquia Theory and applications of partial differential equations file 서울대 변순식
Math Colloquia Variational Methods without Nondegeneracy file POSTECH 변재형
Math Colloquia W-algebras and related topics file 서울대학교 서의린
Math Colloquia Mixing time of random processes file 서울대 서인석
Math Colloquia <2020년도 젊은 과학자상 수상 기념강연> Metastability of stochastic systems file 서울대학교 서인석
Math Colloquia L-function: complex vs. p-adic file 충북대학교 선해상
Math Colloquia Quantitative residual non-vanishing of special values of various L-functions file UNIST 선해상
Math Colloquia 행렬함수 Permanent의 극소값 결정과 미해결 문제들 file 제주대학교/서울대학교 송석준
Math Colloquia 학부생을 위한 강연: Choi's orthogonal Latin Squares is at least 61 years earlier than Euler's file 연세대학교 송홍엽
Math Colloquia Existence of positive solutions for φ-Laplacian systems file 이용훈 수학강연회,특별강연,대중강연
Math Colloquia 학부생을 위한 ε 강연회: Sir Isaac Newton and scientific computing file 서울대학교 신동우
Math Colloquia Towards Trustworthy Scientific Machine Learning: Theory, Algorithms, and Applications file KAIST 신연종
Math Colloquia <학부생을 위한 ε 강연> 압축센싱과 행렬완성 file 서울대 심병효
Math Colloquia <학부생을 위한 ɛ 강연> A mathematical approach to xEV battery system file LG화학 안형준
Math Colloquia 학부생을 위한 강연회: 통신의 New Trend, 그리고 Big Data file KT 전무 양현미
Math Colloquia <학부생을 위한 강연> 사색 정리를 포함하는 Hadwiger의 추측의 변형에 관하여 file KAIST 엄상일
Board Pagination Prev 1 2 3 4 5 6 7 8 9 10 11 Next
/ 11