65 Matching Annotations
  1. Jun 2023
    1. Children develop a succession of different, increasingly accurate, conceptions of the world and it at least appears that they do this as a result of their experience. But how can the concrete particulars of experience become the abstract structures of knowledge?

      I was unfamiliar with Bayesian learning/Bayesian interference before reading this article. I looked it up and found a helpful tool here: https://seeing-theory.brown.edu/bayesian-inference/index.html. Much of the information I read to familiarize myself with the topic referred to it in the context of machine learning. I can see how the idea of "how one should update one’s beliefs upon observing data" can apply to student learning, especially for young kids. Kunin, D., Guo, J., Dae Devlin, T., & Ziang, D. (n.d.). Bayesian inference. Seeing Theory. https://seeing-theory.brown.edu/bayesian-inference/index.html

  2. Jan 2023
  3. Aug 2022
  4. Apr 2022
  5. Aug 2021
  6. Jul 2021
  7. May 2021
  8. Apr 2021
  9. Mar 2021
  10. Feb 2021
  11. Dec 2020
  12. Oct 2020
  13. Sep 2020
  14. Aug 2020
  15. Jul 2020
  16. Jun 2020
  17. May 2020
  18. Apr 2020
  19. Nov 2018
    1. Explaining Deep Learning Models - A Bayesian Non-parametric Approach

      无疑,讨论模型可解释性的 paper 总是让人充满好奇的。 文中说前人据网络的 output 形成了两种解释思路:whitebox/blackbox explanation。此文提出了新black-box方法(general sensitivity level of a target model to specific input dimensions) 通过建立 DMM-MEN。

  20. Sep 2018
    1. in equation B for the marginal of a gaussian, only the covariance of the block of the matrix involving the unmarginalized dimensions matters! Thus “if you ask only for the properties of the function (you are fitting to the data) at a finite number of points, then inference in the Gaussian process will give you the same answer if you ignore the infinitely many other points, as if you would have taken them all into account!”(Rasmunnsen)

      key insight into Gaussian processes

  21. Jul 2018
  22. Jan 2016
  23. Oct 2015