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 28 May 2020

      Here's the thing about AI: you get what you optimize for. If you optimize for a specific skill, like chess or StarCraft, your final system will possess this skill and nothing else. It won't generalize to any other task. To generalize, you must optimize for generality itself.

      26 replies 208 retweets 1,142 likes
      Show this thread
    2. François Chollet‏Verified account @fchollet 28 May 2020

      To be clear, optimizing for task-specific skill can be valuable. It gets you somewhere. But now, we're at a stage in the development of AI where generalization has become, inevitably, the bottleneck to skill acquisition.

      1 reply 13 retweets 154 likes
      Show this thread
    3. François Chollet‏Verified account @fchollet 28 May 2020

      Of course, if you can amass a sufficiently dense sampling of situations within a sufficiently narrow domain, you can always train a machine model -- but it will break down as soon as it encounters anything it has never seen before. That's modern deep learning.

      3 replies 24 retweets 125 likes
      Show this thread
    4. François Chollet‏Verified account @fchollet 28 May 2020

      And for many high-value real-world tasks, that's just about every day. Consider self-driving cars, or domestic robotics. You can't enumerate the set of possible situations a driver might ever encounter -- billions of miles are not nearly enough.

      3 replies 8 retweets 130 likes
      Show this thread
      François Chollet‏Verified account @fchollet 28 May 2020

      You can't even enumerate the set of possible kitchens a robot might operate in. If you want to ever be able to deploy a L5 self-driven system or a human-level domestic robot, you have to figure out how to implement broad cognitive abilities -- beyond task-specific skills.

      3:26 PM - 28 May 2020
      • 18 Retweets
      • 199 Likes
      • Jeremy Diamond ☕️ ChrisMattmann.eth Eric JoAchim Liese Kevin Golan Sukriti Verma Arun Ramji Shanmugam Tim Leonhardt Sarah Frisk Dubsky Jose Mora
      12 replies 18 retweets 199 likes
        1. New conversation
        2. Benedict Evans‏Verified account @benedictevans 28 May 2020
          Replying to @fchollet

          so in a sense, ML is another rules based system.

          1 reply 0 retweets 11 likes
        3. François Chollet‏Verified account @fchollet 28 May 2020
          Replying to @benedictevans

          With rules based on learned distance functions wrt reference points, rather than exact matches. But yes.

          1 reply 2 retweets 13 likes
        4. Show replies
        1. Mark Saroufim‏ @marksaroufim 28 May 2020
          Replying to @fchollet

          Instead of creating a single kitchen bot that can generalize to all kitchens, provide a toolkit and the right visualization libraries so people can train a kitchen bot on a single kitchen.

          0 replies 0 retweets 0 likes
          Thanks. Twitter will use this to make your timeline better. Undo
          Undo
        1. Ronald Delgado‏ @rdelgadoCF 28 May 2020
          Replying to @fchollet

          Do you think those cognitive abilities could eventually come as some kind of emergent behavior, cellular automata style?

          0 replies 1 retweet 1 like
          Thanks. Twitter will use this to make your timeline better. Undo
          Undo
        1. Russell Hawkins‏ @RussellRHawkins 28 May 2020
          Replying to @fchollet

          How did nature produce broad cognitive abilities? The kind we want to create appeared recently, only in the human lineage, but they are based on systems with evolutionary roots going back to the Cambrian explosion. https://link.springer.com/article/10.3758/s13414-019-01760-1 … Evolution can help us understand.

          0 replies 1 retweet 2 likes
          Thanks. Twitter will use this to make your timeline better. Undo
          Undo
        1. New conversation
        2. Hasan Saikat‏ @hasaansaikat 28 May 2020
          Replying to @fchollet

          Intelligence shouldn’t be artificial. We should focus more on how really mind is initialized & progressed throughout the Lifetime inside brain. Why an Apple is called an Apple not something else?

          1 reply 0 retweets 0 likes
        3. Hasan Saikat‏ @hasaansaikat 28 May 2020
          Replying to @hasaansaikat @fchollet

          Does perception & cognitive sense pass through generation? If perception is not constant then what creates imagination?

          0 replies 0 retweets 0 likes
        4. End of conversation
        1. GR-TheArchitect‏ @GrThearchitect 28 May 2020
          Replying to @fchollet

          There is still hope. Nature is optimal! Think for example the principle of least action; we haven’t yet seen a natural process, even at the QM level, which violates it. Think entropy; it’s universal. So you can, in theory, optimize a great deal of natural processes all at once.

          0 replies 0 retweets 0 likes
          Thanks. Twitter will use this to make your timeline better. Undo
          Undo
        1. GR-TheArchitect‏ @GrThearchitect 28 May 2020
          Replying to @fchollet

          Now about using AI to trace the cognitive process, I believe it’s way too soon! The cognitive process is hardly understood let alone ready to be modelled

          0 replies 0 retweets 0 likes
          Thanks. Twitter will use this to make your timeline better. Undo
          Undo
        1. /ˌæʃ'kɑ:n ˌrændʒ'bær/‏ @couzhei 28 May 2020
          Replying to @fchollet

          Hmm, are you just reviewing the materials in your book, Deep Learning with Python? 🤔

          0 replies 0 retweets 0 likes
          Thanks. Twitter will use this to make your timeline better. Undo
          Undo

      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