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 27 Jul 2018

      Whether an AI that plays StarCraft, DotA, or Overwatch succeeds or fails against top players, we'd have learned nothing from the outcome. Wins -- congrats, you've trained on enough data. Fails -- go back, train on 10x more games, add some bells & whistles to your setup, succeed.

      19 replies 74 retweets 329 likes
      Show this thread
    2. François Chollet‏Verified account @fchollet 27 Jul 2018

      Any problem can be treated as a pattern recognition problem if your training data covers a sufficiently dense sampling of the problem space. What's interesting is what happens when your training data is a sparse sampling of the space -- to extrapolate, you will need intelligence.

      8 replies 106 retweets 361 likes
      Show this thread
      François Chollet‏Verified account @fchollet 27 Jul 2018

      Sometimes, it's not about the outcome, it's about what you can learn from the process.

      5:32 AM - 27 Jul 2018
      • 25 Retweets
      • 192 Likes
      • Pranav Abraham Mathews André Cristian (Dezo if you like) geturbley Phuong Edward Wijaya niels #SirDaniel Andymrcc Alfredo De la Fuente
      10 replies 25 retweets 192 likes
        1. New conversation
        2. Marko Jocic‏ @_jocicmarko 27 Jul 2018
          Replying to @fchollet

          If OpenAI Five beats professional players, it would be interesting to see if that is so because it learned some new "tricks" humans didn't discover before. Thus, it might help human players get even better.

          1 reply 0 retweets 0 likes
        3. trylks‏ @trylks 27 Jul 2018
          Replying to @_jocicmarko @fchollet

          Learning something about DotA that helps human players to improve is a likely outcome of OpenAI Five, but that is using AI to research on DotA, not viceversa.

          0 replies 0 retweets 0 likes
        4. End of conversation
        1. Fede Molina‏ @federicomolina 27 Jul 2018
          Replying to @fchollet

          How is this different from AlphaGO?

          0 replies 0 retweets 0 likes
          Thanks. Twitter will use this to make your timeline better. Undo
          Undo
        1. Vincent‏ @bons_vincent 27 Jul 2018
          Replying to @fchollet

          Do you know of any good benchmarks for generalization in machine learning algorithms?

          0 replies 0 retweets 0 likes
          Thanks. Twitter will use this to make your timeline better. Undo
          Undo
        1. VivaDoyers‏ @SunnyD17 27 Jul 2018
          Replying to @fchollet

          Compensate the sparse training data with a physics or rule based model?

          0 replies 0 retweets 0 likes
          Thanks. Twitter will use this to make your timeline better. Undo
          Undo
        1. New conversation
        2. Alejo Rodríguez‏ @prodigious_tech 27 Jul 2018
          Replying to @fchollet

          I do not agree, completely. This is not supervised learning, this is Reinforcement Learning, where the agents extrapolate a complex behavior from raw rewards coming from an environment. If this is pattern recognition, then humans are so.

          1 reply 0 retweets 0 likes
        3. trylks‏ @trylks 27 Jul 2018
          Replying to @prodigious_tech @fchollet

          We can model human intelligence as pattern recognition, but we are *extremely good* at it We need zero samples, a description (words) may be enough to create a pattern (BTW it is holistic/hierarchical), recognize it, and be disappointed (high entropy) by it, because WTF is this:pic.twitter.com/hUQu35h8ev

          0 replies 0 retweets 0 likes
        4. End of conversation
        1. trylks‏ @trylks 27 Jul 2018
          Replying to @fchollet

          I may be biased, but IMHO StarCraft is a different beast due to fog of war, e.g. may choose to lose a unit to see something For the first time, actively seeking to update a theory of mind/strategy of the rival and adapting to it _might be necessary_ to defeat best human players

          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