Extra Form
강연자 신연종
date 2022-10-13


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.

첨부 '1'
  1. 17Oct
    by 김수현
    in 수학강연회

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

  2. Elliptic equations with singular drifts in critical spaces

  3. Contact topology of singularities and symplectic fillings

  4. Regularity theory for non-autonomous elliptic equations in divergence form

  5. <2020년도 젊은 과학자상 수상 기념강연> Metastability of stochastic systems

  6. Geometric Langlands theory: A bridge between number theory and physics

  7. Noise-induced phenomena in stochastic heat equations

  8. Mirror symmetry of pairings

  9. A dissipative effect on some PDEs with physical singularity

  10. <학부생을 위한 ɛ 강연> Secure computation: Promise and challenges

  11. Geometric structures and representation spaces

  12. <정년퇴임 기념강연> 리만 가설에 관련된 옌센 다항식의 영점

  13. Infinite order rationally slice knots

  14. Random matrices and operator algebras

  15. Symplectic topology and mirror symmetry of partial flag manifolds

  16. 돈은 어떻게 우리 삶에 돈며들었는가? (불확실성 시대에 부는 선형적으로 증가하는가?)

  17. <학부생을 위한 ɛ 강연> Mathematics and music: Pythagoras, Bach, Fibonacci and AI

  18. Topological surgery through singularity in mean curvature flow

  19. Heavy-tailed large deviations and deep learning's generalization mystery

  20. Diophantine equations and moduli spaces with nonlinear symmetry

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