Niloofar

@galaxygarden23

Fatemeh (Niloofar) Mireshghallah- PhD student at UC San Diego, CSE /Privacy, Machine Learning, Systems research

Vrijeme pridruživanja: svibanj 2013.

Tweetovi

Blokirali ste korisnika/cu @galaxygarden23

Jeste li sigurni da želite vidjeti te tweetove? Time nećete deblokirati korisnika/cu @galaxygarden23

  1. Prikvačeni tweet
    7. lip 2019.

    Excited to be presenting "Shredder" at the workshop on Security and Privacy of Machine Learning next week!

    Poništi
  2. proslijedio/la je Tweet

    Become a better communicator overnight: - Replace every “but” you can with an “and” - Never start a sentence with “no” or “disagree” - Only give feedback if there’s a chance it will be implemented - Tell people you will be late before you are late - Bias to overcommunicating

    Poništi
  3. proslijedio/la je Tweet
    prije 14 sati

    Tesla AI recruitment 🔥 “A PhD is definitely not required. All that matters is a deep understanding of AI and ability to implement NNs in a way that is actually useful (latter point is what’s truly hard). Don’t care if you finished high school.”

    Prikaži ovu nit
    Poništi
  4. prije 14 sati

    Reminds me of encryption :))

    Poništi
  5. proslijedio/la je Tweet
    1. velj

    I'm Chinese, but I'm not a virus I know everyone is afraid of the virus, but no projudice, plz.

    Poništi
  6. proslijedio/la je Tweet
    prije 23 sata

    It is amazing that some fathom that GPT-2 just needs more data to reach comprehension and intelligent. well portrays how misguided is this notion.

    Prikaži ovu nit
    Poništi
  7. proslijedio/la je Tweet
    5. lip 2019.

    I am incredibly excited to announce the next big thing. I recently founded a new company with a world class group of cofounders. Here is our website - and we are hiring -

    Poništi
  8. proslijedio/la je Tweet
    1. velj

    In case you need it: You did great this week. Be yourself and enjoy your weekend. You deserve to be happy. Everyday is a new opportunity. Love yourself.

    Prikaži ovu nit
    Poništi
  9. proslijedio/la je Tweet
    31. sij

    Debugging Tensor Flow in grad school was always a challenge! Switching to PyTorch really increased my productivity, giving me time to focus on things that matter!

    Poništi
  10. proslijedio/la je Tweet
    30. sij

    For a quick break from scary tweets from all over ... Let’s never forget humans are amazing and the universe is beautiful! ❤️

    Poništi
  11. proslijedio/la je Tweet
    30. sij

    Learnt a lot from podcast on , a way of collecting about the population while protecting the privacy of individual users by adding noise to the data 🔏here's the podcast:

    Poništi
  12. proslijedio/la je Tweet
    29. sij

    Excited to release a library for explaining ML models using counterfactual examples. The idea is simple--explain a prediction by the minimal changes that would lead to a different outcome--but turns out generating a diverse set is challenging. 1/3

    Prikaži ovu nit
    Poništi
  13. 29. sij

    The program is out, and our paper "Shredder: Learning Noise Distributions to Protect Inference Privacy" is the first talk of the conference! So excited! The preprint to the paper is available here:

    Poništi
  14. proslijedio/la je Tweet
    28. sij

    Privacy: * model inversion attack, where the attacker can recover the training data from queries to the model [ THIS SHOULD BE BETTER KNOWN IT'S A REAL PROBLEM FOR DATA RETENTION AS WELL ]

    Prikaži ovu nit
    Poništi
  15. 27. sij

    Great talk by Sadia Afroz on adversarial examples in malware detection, how the problem is different from image classification and the current approaches for dealing with this problem.

    Poništi
  16. proslijedio/la je Tweet
    25. sij

    What GPT-2 accidentally reveals about nature, nurture, and the challenge of building intelligence. Prelude to a longer piece on how to best advance AI over the next decade 😊

    Poništi
  17. 26. sij

    Awesome piece! Looking forward to reading more!

    Poništi
  18. proslijedio/la je Tweet
    25. sij

    Nice job by . I agree on every point. (Well, except for the one reference to "genuine understanding"...) 1/

    Prikaži ovu nit
    Poništi
  19. proslijedio/la je Tweet
    25. sij

    Coming at noon PT, some thoughts on GPT-2 and what it accidentally reveals about the challenge of building intelligence. Prelude to a longer piece on how to best advance AI over the next decade 😊

    Poništi
  20. proslijedio/la je Tweet
    23. sij

    Google Dataset Search is now officially out of beta. "Dataset Search has indexed almost 25 million of these datasets, giving you a single place to search for datasets & find links to where the data is." Nice work, Natasha Noy and everyone else involved!

    Prikaži ovu nit
    Poništi
  21. 24. sij

    I hope there is video stream of available, so that students like myself who cannot exit the U.S. due to visa complications can still be able to benefit from all the great talks and workshops.

    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:

    ·