Skip to content
  • Home Home Home, current page.
  • Moments Moments Moments, current page.

Saved searches

  • Remove
  • In this conversation
    Verified accountProtected Tweets @
Suggested users
  • Verified accountProtected Tweets @
  • Verified accountProtected Tweets @
  • Language: English
    • Bahasa Indonesia
    • Bahasa Melayu
    • Català
    • Čeština
    • Dansk
    • Deutsch
    • English UK
    • Español
    • Filipino
    • Français
    • Hrvatski
    • Italiano
    • Magyar
    • Nederlands
    • Norsk
    • Polski
    • Português
    • Română
    • Slovenčina
    • Suomi
    • Svenska
    • Tiếng Việt
    • Türkçe
    • Ελληνικά
    • Български език
    • Русский
    • Српски
    • Українська мова
    • עִבְרִית
    • العربية
    • فارسی
    • मराठी
    • हिन्दी
    • বাংলা
    • ગુજરાતી
    • தமிழ்
    • ಕನ್ನಡ
    • ภาษาไทย
    • 한국어
    • 日本語
    • 简体中文
    • 繁體中文
  • Have an account? Log in
    Have an account?
    · Forgot password?

    New to Twitter?
    Sign up
zeynep's profile
zeynep tufekci
zeynep tufekci
zeynep tufekci
Verified account
@zeynep

Tweets

zeynep tufekciVerified account

@zeynep

Complex systems, wicked problems. Society, technology, science and more. @UNC professor. @NYTimes columnist. My newsletter is @insight: http://www.theinsight.org 

floating in a most peculiar way
theinsight.org
Joined August 2009

Tweets

  • © 2022 Twitter
  • About
  • Help Center
  • Terms
  • Privacy policy
  • Cookies
  • Ads info
Dismiss
Previous
Next

Go to a person's profile

Saved searches

  • Remove
  • In this conversation
    Verified accountProtected Tweets @
Suggested users
  • Verified accountProtected Tweets @
  • Verified accountProtected Tweets @

Promote this Tweet

Block

  • Tweet with a location

    You can add location information to your Tweets, such as your city or precise location, from the web and via third-party applications. You always have the option to delete your Tweet location history. Learn more

    Your lists

    Create a new list


    Under 100 characters, optional

    Privacy

    Copy link to Tweet

    Embed this Tweet

    Embed this Video

    Add this Tweet to your website by copying the code below. Learn more

    Add this video to your website by copying the code below. Learn more

    Hmm, there was a problem reaching the server.

    By embedding Twitter content in your website or app, you are agreeing to the Twitter Developer Agreement and Developer Policy.

    Preview

    Why you're seeing this ad

    Log in to Twitter

    · Forgot password?
    Don't have an account? Sign up »

    Sign up for Twitter

    Not on Twitter? Sign up, tune into the things you care about, and get updates as they happen.

    Sign up
    Have an account? Log in »

    Two-way (sending and receiving) short codes:

    Country Code For customers of
    United States 40404 (any)
    Canada 21212 (any)
    United Kingdom 86444 Vodafone, Orange, 3, O2
    Brazil 40404 Nextel, TIM
    Haiti 40404 Digicel, Voila
    Ireland 51210 Vodafone, O2
    India 53000 Bharti Airtel, Videocon, Reliance
    Indonesia 89887 AXIS, 3, Telkomsel, Indosat, XL Axiata
    Italy 4880804 Wind
    3424486444 Vodafone
    » See SMS short codes for other countries

    Confirmation

     

    Welcome home!

    This timeline is where you’ll spend most of your time, getting instant updates about what matters to you.

    Tweets not working for you?

    Hover over the profile pic and click the Following button to unfollow any account.

    Say a lot with a little

    When you see a Tweet you love, tap the heart — it lets the person who wrote it know you shared the love.

    Spread the word

    The fastest way to share someone else’s Tweet with your followers is with a Retweet. Tap the icon to send it instantly.

    Join the conversation

    Add your thoughts about any Tweet with a Reply. Find a topic you’re passionate about, and jump right in.

    Learn the latest

    Get instant insight into what people are talking about now.

    Get more of what you love

    Follow more accounts to get instant updates about topics you care about.

    Find what's happening

    See the latest conversations about any topic instantly.

    Never miss a Moment

    Catch up instantly on the best stories happening as they unfold.

    1. zeynep tufekci‏Verified account @zeynep 24 Nov 2018
      Replying to @stevesi

      We had this disagreement over Twitter before That ML models aren't interpretable (except obvious things which wouldn't need ML model if that's all there was) doesn't seem to be controversial among practitioners or CS professors.

      2 replies 1 retweet 0 likes
    2. zeynep tufekci‏Verified account @zeynep 24 Nov 2018
      Replying to @zeynep @stevesi

      I look at the interpretability work, and it seems promising in things like visual systems where humans, too, can literally eyeball what's going on in the layers, but not for much else. If I see work that succesfully interprets and rules out, I'll change my mind. Please do send.

      0 replies 0 retweets 1 like
    3. This Tweet is unavailable.
    4. zeynep tufekci‏Verified account @zeynep 24 Nov 2018
      Replying to @stevesi

      Dunno what G maps uses for routes. (It's the kind of thing that existed before current boom in ML, pre Le et al., 2012) : The ones I care about: hiring, ranking, recommending, rating using ML. If any of those were interpretable, they could've been programmed symbolically, btw.

      2 replies 0 retweets 0 likes
    5. zeynep tufekci‏Verified account @zeynep 24 Nov 2018
      Replying to @zeynep @stevesi

      In those, I routinely ask practicioners, CS professors for how interpretation work is going, and I bring up scenarios and ask if they can rule them out. I don't get positive answers. I read the interpretability papers, too. Don't see much progress.

      0 replies 0 retweets 1 like
    6. This Tweet is unavailable.
    7. Alex Clemmer  🔥 🔥 🔥 😅 🔥 🔥 🔥‏ @hausdorff_space 24 Nov 2018
      Replying to @stevesi @zeynep

      Steven, as co-recipient of SIGIR's paper from 2017, I have to admit that I honestly do not understand your use of search engines as an example of why ml is interpretable. It does seem like the consensus is that ml is usually very hard to interpret, and I don't see this refuting.

      1 reply 0 retweets 3 likes
    8. Alex Clemmer  🔥 🔥 🔥 😅 🔥 🔥 🔥‏ @hausdorff_space 24 Nov 2018
      Replying to @hausdorff_space @stevesi @zeynep

      SIGIR's best* paper. (I'm not claiming to be an expert in search per se, btw... But as someone with practical exposure to the subject, your responses do trigger alarm bells. )

      0 replies 0 retweets 0 likes
    9. This Tweet is unavailable.
    10. Alex Clemmer  🔥 🔥 🔥 😅 🔥 🔥 🔥‏ @hausdorff_space 24 Nov 2018
      Replying to @stevesi @zeynep

      Could be wrong I don't read her points as being fundamental statements about the interpretability of ml models. I read them as deep skepticism that it is socially responsible to apply models to specific classes of problems, mostly because we lack good tools an op. expertise

      1 reply 0 retweets 3 likes
      zeynep tufekci‏Verified account @zeynep 24 Nov 2018
      Replying to @hausdorff_space @stevesi

      And that the shift from what’s called symbolic programming etc. to connectionist approaches is a big shift. It’s a different animal, re:interpretability. There is a program if research, but so is there for the brain. Arguably we’ll never fully be able to interpret either.

      4:03 PM - 24 Nov 2018
      1 reply 0 retweets 0 likes
        1. New conversation
        2. Alex Clemmer  🔥 🔥 🔥 😅 🔥 🔥 🔥‏ @hausdorff_space 24 Nov 2018
          Replying to @zeynep @stevesi

          I actually think the question of interpretability is probably ill-formed. I don't think it's an accident that much of the open theory is asking what we can guarantee about models (e.g., algorithmic fairness, statistical guarantees of deep learning, etc.)

          1 reply 0 retweets 1 like
        3. Alex Clemmer  🔥 🔥 🔥 😅 🔥 🔥 🔥‏ @hausdorff_space 24 Nov 2018
          Replying to @hausdorff_space @zeynep @stevesi

          Even prima facie, these sorts of tools _look_ very different from the sorts of tools we'd use to debug "normal" systems. This is where a lot of the discomfort is coming from. If we don't know what we can guarantee about models, what exactly does that mean for us in practice?

          1 reply 0 retweets 1 like
        4. Show replies

      Loading seems to be taking a while.

      Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.

        Promoted Tweet

        false

        • © 2022 Twitter
        • About
        • Help Center
        • Terms
        • Privacy policy
        • Cookies
        • Ads info