Skip to content
By using Twitter’s services you agree to our Cookies Use. We and our partners operate globally and use cookies, including for analytics, personalisation, and ads.
  • Home Home Home, current page.
  • About

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
fchollet's profile
François Chollet
François Chollet
François Chollet
Verified account
@fchollet

Tweets

François CholletVerified account

@fchollet

Deep learning @google. Creator of Keras. Author of 'Deep Learning with Python'. Opinions are my own.

United States
fchollet.com
Joined August 2009

Tweets

  • © 2021 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. François Chollet‏Verified account @fchollet Oct 20

      François Chollet Retweeted Khalid Saifullah

      And why would you restrict yourself to the original encoding space and to the Euclidean distance? These are completely arbitrary choices (and completely biased). There's an infinity of possibly encodings of the data you could have chosen, and an infinity of distance functions.https://twitter.com/k_saifullaah/status/1409972975835566081 …

      François Chollet added,

      Khalid Saifullah @k_saifullaah
      Replying to @fchollet
      Kinda puzzled with this and @ylecun's extrapolation idea, Like, a sample from my validation set isn't a linear combination of my training set, then how can I call it interpolation and not extrapolation?
      5 replies 8 retweets 70 likes
      Show this thread
    2. François Chollet‏Verified account @fchollet Oct 20

      Perhaps a different culture would always present data on a sphere and would use geodesic distance as the default. I don't know! There should no reason whatsoever to expect an arbitrary encoding and an arbitrary distance to result in an interpolative problem space.

      1 reply 0 retweets 16 likes
      Show this thread
    3. François Chollet‏Verified account @fchollet Oct 20

      The correct encoding and distance to use is of course the ones that are natural to the data -- that is to say, the latent manifold of the data. Which *is* an interpolative space for many problems (hence why deep learning models are able to generalize).

      3 replies 5 retweets 27 likes
      Show this thread
    4. Joscha Bach‏ @Plinz Oct 20
      Replying to @fchollet

      There is an additional factor: while the function used to describe the data should allow a natural representation of the latent space, the function needs also be efficient to discover, construct, parameterize and represent. (That's why Euclidean representations are ubiquitous.)

      1 reply 0 retweets 10 likes
      François Chollet‏Verified account @fchollet Oct 20
      Replying to @Plinz

      Absolutely! You can't leverage the latent manifold (or rather, an approximation of it) unless you can represent it (easy part) and learn it (hard part).

      11:11 AM - 20 Oct 2021
      • 1 Like
      • Shivam Maurya
      0 replies 0 retweets 1 like

      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

        • © 2021 Twitter
        • About
        • Help Center
        • Terms
        • Privacy policy
        • Cookies
        • Ads info