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 27 Jan 2018

    Biggest question in AI, and no one has a clue. We need new mathematical abstractions of abstraction. No, not category theory.pic.twitter.com/3f22R6ue6f

    6:09 PM - 27 Jan 2018
    • 71 Retweets
    • 276 Likes
    • Maddison Dickinson Mark C.F. Sousa Murat Duman Christopher Wolff Lois Patterson Bernard Vander Beken marci Kevin D. Keck Think & Smile
    30 replies 71 retweets 276 likes
      1. New conversation
      2. javier  💚‏ @infrahumano 27 Jan 2018
        Replying to @fchollet

        What is the piece about abstraction that category theory lacks?

        3 replies 0 retweets 8 likes
      3. CoinMathematics‏ @CoinMathematics 27 Jan 2018
        Replying to @infrahumano @fchollet

        Was wondering this myself. Kind of hoping the response is more arrows.

        0 replies 0 retweets 8 likes
      4. End of conversation
      1. Robert E. P. Levy (rplevy@gmail.com)‏ @rplevy 27 Jan 2018
        Replying to @fchollet

        I think there's low-hanging fruit in cognitive semantics such as usage-based approaches to grammar, conceptual metaphor etc. And DL/RL work has progressed on basic situated agents to where it may be worthwile to revisit grounding abstractions in experience using those approaches.

        0 replies 0 retweets 5 likes
        Thanks. Twitter will use this to make your timeline better. Undo
        Undo
      1. This Tweet is unavailable.
      2. DoomscrollPro‏ @DoomscrollPro 27 Jan 2018
        Replying to @PabloCater @fchollet

        In what ways are purely mathematical models of AI architectures insufficient for efficiently explaining the relationship between intermediate fine scale effects of model parametrization and terminal states?

        0 replies 0 retweets 0 likes
      3. End of conversation
      1. A.) Quail‏ @dsdtzero 27 Jan 2018
        Replying to @fchollet

        “Contextual” category theory maybe? It seems we treat everything in this Franken-equilibrium states approach when the real problem is we don’t have a way to produce a satisfying taxonomy of /bf{dynamical} classes. They have to exists in certain limited contexts. I can feel em

        0 replies 0 retweets 3 likes
        Thanks. Twitter will use this to make your timeline better. Undo
        Undo
      1. New conversation
      2. Max Bendick  🎺‏ @MaxBendick 27 Jan 2018
        Replying to @fchollet

        Something between category theory and information theory perhaps.

        1 reply 0 retweets 3 likes
      3. Max Bendick  🎺‏ @MaxBendick 27 Jan 2018
        Replying to @MaxBendick @fchollet

        Biggest questions for me are finding/defining types and functors in differentiable programming. They probably need to be fuzzier than what category theorists are used to.

        1 reply 0 retweets 1 like
      4. Show replies
      1. New conversation
      2. Nicholas Guttenberg‏ @ngutten 27 Jan 2018
        Replying to @fchollet

        Perhaps renormalization group applied to understanding which approximate summary statistics will still have divergent terms when used to approximate stuff infinitely far away from the actual distributions they summarize, and how to systematically suppress those divergences.

        1 reply 0 retweets 1 like
      3. Chaotic Butter Flies‏ @botminds 27 Jan 2018
        Replying to @ngutten @fchollet

        This seems too specific to cover all of abstraction.

        1 reply 0 retweets 0 likes
      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

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