Tweetovi

Blokirali ste korisnika/cu @hima_lakkaraju

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

  1. Prikvačeni tweet

    Attention folks at AIES -- we have two talks at the session on "Explanation" from 130pm to 245pm today!! Paper 1: Fooling post hoc explanation methods (with , Sophie, , ) Paper 2: Manipulating user trust with misleading explanations (with Osbert).

    Prikaži ovu nit
    Poništi
  2. We are also presenting this research at workshop at today!!!!

    Prikaži ovu nit
    Poništi
  3. Just noticed that there is an HBR article that discusses our recent work on fooling ML explanation methods: . Yayy! Our paper:

    Poništi
  4. 30. sij

    Modern work is the enemy of thought. Just as you can't hurry yourself to sleep, you can't stress yourself to clear thinking.

    Poništi
  5. This will be done as part of the doctoral course offered by Technology and Operations Management (TOM) unit.

    Prikaži ovu nit
    Poništi
  6. I am excited to be teaching a set of lectures on "introduction to machine learning for social scientists" at this semester. More details coming soon!

    Prikaži ovu nit
    Poništi
  7. I found this slipped under my office door today. Little joys of my job :) :)

    Poništi
  8. 15. sij

    Asked by a colleague at a different dept: which CS/AI/ML conferences were highly competitive? To help evaluate faculty coming up for promotion. They are calibrated for journals but not conferences. I answered quest. narrowly but do U know comprehensive evaluation or ranking?

    Poništi
  9. Today's dose of inspiration: Michelle Obama has some very sound advice on tackling imposter syndrome

    Poništi
  10. 6. sij

    Most popular computer science paper of the day: "How can we fool LIME and SHAP? Adversarial Attacks on Post hoc Explanation Methods"

    Poništi
  11. 2. sij

    As director (Center for Research in Computation and Society ) I am pleased to bring to attention upcoming "AI for Social Impact" workshop for PhD students, postdocs & junior researchers: Apply by January 10. Travel funding.

    Poništi
  12. 14. Had a lot of fun and happy memories too, ofcourse :) -- e.g., saw tears of joy in my parents eyes during my PhD convocation. 15. Married my best friend 16. Bought a house All in all, I am ready to step into the next decade (as a somewhat more cynical adult).

    Prikaži ovu nit
    Poništi
  13. 12. Experienced loneliness, pain, dissatisfaction, burn out. Felt inadequate, unappreciated, and discriminated against. 13. Learned that life is often far from perfect and the only way to live is to make the best of the cards that you are handed, and just have a good time [4/n]

    Prikaži ovu nit
    Poništi
  14. 10. Met and dealt with a lot of people in the world (and in academia) who inspired me to do better professionally and personally 11. Met a lot of other people too because of whom I lost faith in humanity (DM me to know the full list :p) [3/n]

    Prikaži ovu nit
    Poništi
  15. 4. Relocated from India to Bay area 5. Relocated from Bay area to Boston 6. Started and finished my PhD 7. Survived major health situations 8. Accepted my first faculty job (will start on 1/1/2020 - yayy!) 9. Taught my first ever (full fledged) course [2/n]

    Prikaži ovu nit
    Poništi
  16. A recap of my past decade: 1. Started doing research 2. Wrote a bunch of papers and collaborated with some awesome people 3. Got some external recognition for my work e.g., MIT Tech Review 35 Under 35 [1/n]

    Prikaži ovu nit
    Poništi
  17. 26. pro 2019.

    Bayesian methods are *especially* compelling for deep neural networks. The key distinguishing property of a Bayesian approach is marginalization instead of optimization, not the prior, or Bayes rule. This difference will be greatest for underspecified models like DNNs. 1/18

    Prikaži ovu nit
    Poništi
  18. "...when YOU hear about a case...your priors should tell you that it’s very likely that some unusually bad behavior happened...She invariably has faced much, much more than you are aware of. If you know about seemingly minor problems, chances are, she really needs your help."

    Poništi
  19. Excited to be featured on this list alongside other amazing researchers! Thank you so much for the honor, Lighthouse3!

    Poništi
  20. 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:

    ·