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.

    François Chollet‏Verified account @fchollet 18 Apr 2020

    The dimensionality of data isn't the dimensionality of the encoding medium (e.g. images -> 2D data). All data can be re-encoded with a different number of dimensions. What matters is the dimensionality of the latent manifold. The structure of correlations in your data.

    12:16 PM - 18 Apr 2020
    • 105 Retweets
    • 682 Likes
    • Alejandro Piad Morffis ReJ @ NMA21 🚀 Renaldas Zioma prod. by Most High Tim Scarfe Kim Jong Kardashian Un mec vachement sérieux 🔻 Siren Hakimi उत्तराषाढा rowan callahan
    16 replies 105 retweets 682 likes
      1. New conversation
      2. François Chollet‏Verified account @fchollet 18 Apr 2020

        François Chollet Retweeted Pedro Domingos

        So it is definitely not the case that painting is 2D, music is 1D, and mathematics is infD. Mathematics, like computing, is typically encoded as manipulations on strings of symbols, so by that logic it would be a 1D problem.https://twitter.com/pmddomingos/status/1251341882828795904 …

        François Chollet added,

        Pedro Domingos @pmddomingos
        One dimension: Music Two dimensions: Painting Three dimensions: Sculpture Infinite dimensions: Mathematics
        5 replies 9 retweets 94 likes
        Show this thread
      3. François Chollet‏Verified account @fchollet 18 Apr 2020

        Arguably all of these domains have the same "dimension", which is the intrinsic dimensionality of the human mind.

        6 replies 8 retweets 94 likes
        Show this thread
      4. François Chollet‏Verified account @fchollet 18 Apr 2020

        (I'm expecting pedantic, braindead replies about how mathematics is not a product of the human mind 😉)

        9 replies 2 retweets 76 likes
        Show this thread
      5. End of conversation
      1. Rajiv Parmar‏ @raj_talus 18 Apr 2020
        Replying to @fchollet

        Is there a lot of work going on in data compression? Last I checked it was only two forms of mathematics and applied to the fax, video and music but have there been any good advances lately? I should think it is highly applicable to 5G

        0 replies 0 retweets 0 likes
        Thanks. Twitter will use this to make your timeline better. Undo
        Undo
      1. New conversation
      2. /home/ggdupont‏ @ggdupont 18 Apr 2020
        Replying to @fchollet

        I can only agree on this. This is often why NLP is sometimes perceived as "simpler" than image/video since it can be encoded efficiently. But latent semantic space of language is much bigger (could I dare to say infinite?).

        1 reply 0 retweets 25 likes
      3. Xander Steenbrugge‏ @xsteenbrugge 18 Apr 2020
        Replying to @ggdupont @fchollet

        This is an interesting thought.. Can one speak more things than one can see? Or can everything that can be spoken also be (visually) perceived? They're definitely overlapping sets, but I'm not sure which is bigger..

        1 reply 0 retweets 7 likes
      4. Show replies
      1. New conversation
      2. zTey‏ @DecioAguiar 18 Apr 2020
        Replying to @fchollet

        @arthurands

        1 reply 0 retweets 1 like
      3. arthu‏ @1aands 18 Apr 2020
        Replying to @DecioAguiar @fchollet

        Isso me lembra da correlações de pcas com os dados normalizados, pra garantir os principais pcas

        0 replies 0 retweets 1 like
      4. End of conversation
      1. Sandeep Sharma‏ @sandeepkaushik 18 Apr 2020
        Replying to @fchollet

        I have not seen Dimensions explained in simpler english

        1 reply 0 retweets 1 like
        Thanks. Twitter will use this to make your timeline better. Undo
        Undo
      1. New conversation
      2. Wey Tu Yung‏ @bronzeagepapi 18 Apr 2020
        Replying to @fchollet

        Reminds me of ”the map is not the territory”. Isn't the encoding just a projection from one dimension to another? Question: With multimodal data (e.g. image caption), what can be considered the dimension of the latent manifold within the model?

        1 reply 0 retweets 5 likes
      3. Drago Indjic/Инђић‏ @dindjic 18 Apr 2020
        Replying to @bronzeagepapi @fchollet

        @DanceGrist now add some music and dance

        0 replies 0 retweets 1 like
      4. End of conversation

    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