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'
  1. 04Apr
    by 김수현
    in Math Colloquia

    <학부생을 위한 ɛ 강연> Introduction to the incompressible Navier-Stokes equations

  2. 05Nov
    by 김수현
    in Math Colloquia

    Essential dimension of simple algebras

  3. 10May
    by 김수현
    in Math Colloquia

    1 is big enough to understand 3

  4. 07Nov
    by Editor
    in Math Colloquia

    학부생을 위한 강연: Introduction to partial differential equations

  5. 12Sep
    by 김수현
    in Math Colloquia

    Theory and applications of partial differential equations

  6. 07Nov
    by Editor
    in Math Colloquia

    Variational Methods without Nondegeneracy

  7. 13Sep
    by 김수현
    in Math Colloquia

    W-algebras and related topics

  8. 21Sep
    by 김수현
    in Math Colloquia

    Mixing time of random processes

  9. 13May
    by 김수현
    in Math Colloquia

    <2020년도 젊은 과학자상 수상 기념강연> Metastability of stochastic systems

  10. 07Nov
    by Editor
    in Math Colloquia

    L-function: complex vs. p-adic

  11. 01Nov
    by 김수현
    in Math Colloquia

    Quantitative residual non-vanishing of special values of various L-functions

  12. 07Nov
    by Editor
    in Math Colloquia

    행렬함수 Permanent의 극소값 결정과 미해결 문제들

  13. 07Nov
    by Editor
    in Math Colloquia

    학부생을 위한 강연: Choi's orthogonal Latin Squares is at least 61 years earlier than Euler's

  14. 20May
    by 김수현
    in Math Colloquia

    Existence of positive solutions for φ-Laplacian systems

  15. 07Nov
    by Editor
    in Math Colloquia

    학부생을 위한 ε 강연회: Sir Isaac Newton and scientific computing

  16. 17Oct
    by 김수현
    in Math Colloquia

    Towards Trustworthy Scientific Machine Learning: Theory, Algorithms, and Applications

  17. 13Jun
    by 김수현
    in Math Colloquia

    <학부생을 위한 ε 강연> 압축센싱과 행렬완성

  18. 04Apr
    by 김수현
    in Math Colloquia

    <학부생을 위한 ɛ 강연> A mathematical approach to xEV battery system

  19. 07Nov
    by Editor
    in Math Colloquia

    학부생을 위한 강연회: 통신의 New Trend, 그리고 Big Data

  20. 20May
    by 김수현
    in Math Colloquia

    <학부생을 위한 강연> 사색 정리를 포함하는 Hadwiger의 추측의 변형에 관하여

Board Pagination Prev 1 2 3 4 5 6 7 8 9 10 11 12 Next
/ 12