Dylan Slack

@dylanslack20

CS Ph.D. student at UC Irvine working on interpretability and fairness in machine learning.

Newport Beach, CA
Vrijeme pridruživanja: ožujak 2019.

Tweetovi

Blokirali ste korisnika/cu @dylanslack20

Jeste li sigurni da želite vidjeti te tweetove? Time nećete deblokirati korisnika/cu @dylanslack20

  1. Prikvačeni tweet
    9. sij

    Ever wondered when you shouldn't use a fair ML model? Pleased to share our new paper in "Fairness Warnings & Fair-MAML: Learning Fairly from Minimal Data " (w/ , twitterless Emile) where we investigate such questions.

    Prikaži ovu nit
    Poništi
  2. proslijedio/la je Tweet

    In case you're wondering "who is this [exciting, vibrant, fabulous] new conference handle in my timeline?", we're now rather than . You don't need to do anything — except probably battle your Twitter caches and muscle memory.

    Prikaži ovu nit
    Poništi
  3. proslijedio/la je Tweet
    30. sij
    Poništi
  4. proslijedio/la je Tweet
    30. sij

    Huge congrats to exec committee founding members: Sorelle Friedler, , !! Much gratitude for all you've done for the community!

    Poništi
  5. proslijedio/la je Tweet
    30. sij

    The recent work just mentioned on how explanations can be gamed is by et al:

    Poništi
  6. proslijedio/la je Tweet
    28. sij
    Poništi
  7. proslijedio/la je Tweet
    28. sij

    This fairness portability problem discuss is very real. One version of the Idaho pretrial risk assessment bill required validation, but did not specify that they should be validated *in Idaho*.

    Poništi
  8. 26. sij

    We'll also be presenting a version of this paper at the SafeAI workshop at AAAI. If you're at any of these events and want to chat, please reach out!

    Prikaži ovu nit
    Poništi
  9. 26. sij

    Next week, I'll be at AIES presenting a paper on post-hoc interpretation attack techniques "Fooling LIME and SHAP: Adversarial Attacks on Post hoc Explanation Methods" ().

    Prikaži ovu nit
    Poništi
  10. 26. sij

    Exciting next couple weeks presenting work! I'll be at FAT* this week to talk about our recent paper "Fairness Warnings & Fair-MAML: Learning Fairly from Minimal Data" ()

    Prikaži ovu nit
    Poništi
  11. proslijedio/la je Tweet
    Poništi
  12. proslijedio/la je Tweet
    14. sij

    The list of accepted papers for AIES is now also available!

    Poništi
  13. proslijedio/la je Tweet
    14. sij

    We (Haverford Chemistry) are looking for a Visiting Assistant Professor to join our team! This represents and exciting opportunity to grow as a teacher, mentor, and researcher alongside some pretty amazing students. Please spread the word!

    Prikaži ovu nit
    Poništi
  14. 13. sij

    Check out this course! Particularly nice curation of material, albeit in my somewhat biased opinion.

    Poništi
  15. 9. sij

    We (1) provide Fairness Warnings, a method that suggests interpretable boundary conditions where a fairly trained model may behave unfairly and (2) provide a Fair-MAML: a meta-learning approach to training fair models from few tuning instances.

    Prikaži ovu nit
    Poništi
  16. proslijedio/la je Tweet

    Proud of this paper, which led by Justin Otter '19 - a student supervised by me (first one!). With and

    Poništi
  17. proslijedio/la je Tweet
    13. pro 2019.
    Poništi
  18. 13. pro 2019.
    Poništi
  19. 12. pro 2019.

    Check out @CharlieMarx9 and at NeurIPS poster #107! Feature correlation is confusing in influence methods and they have answers!

    Poništi
  20. proslijedio/la je Tweet
    Prikaži ovu nit
    Poništi

Čini se da učitavanje traje već neko vrijeme.

Twitter je možda preopterećen ili ima kratkotrajnih poteškoća u radu. Pokušajte ponovno ili potražite dodatne informacije u odjeljku Status Twittera.

    Možda bi vam se svidjelo i ovo:

    ·