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. ANTIREZ‏ @antirez 25 Sep 2016

      With BPROP training I get 2.3% of errors in MNIST with just 1000 hidden units 2-layers net, no convolution layers. Pretty good AFAIK.

      3 replies 0 retweets 8 likes
    2. François Chollet‏Verified account @fchollet 25 Sep 2016
      Replying to @antirez

      actually that setup should get you to 1.4-1.5 easily.

      3 replies 0 retweets 1 like
    3. ANTIREZ‏ @antirez 25 Sep 2016
      Replying to @fchollet

      p.s. very important: I’m talking about numbers that don’t transform the original data set in any way.

      1 reply 0 retweets 0 likes
    4. François Chollet‏Verified account @fchollet 25 Sep 2016
      Replying to @antirez

      this should be the exact same as the setup you describe: https://gist.github.com/fchollet/ac238179b7752d24717368c45a8db2a7 … goes to 1.8-1.7, down to 1.4 when adding dropout.

      5 replies 0 retweets 3 likes
    5. ANTIREZ‏ @antirez 25 Sep 2016
      Replying to @fchollet

      oh also I see that the cost function is different in your case, I’m using RMS which is not ideal with softmax AFAIK.

      1 reply 0 retweets 0 likes
    6. François Chollet‏Verified account @fchollet 25 Sep 2016
      Replying to @antirez

      you should be using cross entropy. Probability distributions are not an Euclidean space.

      2 replies 0 retweets 0 likes
    7. ANTIREZ‏ @antirez 25 Sep 2016
      Replying to @fchollet

      for this problem for sure, but for the random Redis application of discovering data from users or alike?

      1 reply 0 retweets 0 likes
      François Chollet‏Verified account @fchollet 25 Sep 2016
      Replying to @antirez

      What are your targets?

      3:16 PM - 25 Sep 2016
      4 replies 0 retweets 0 likes
        1. ANTIREZ‏ @antirez 25 Sep 2016
          Replying to @fchollet

          I’ve the feeling that NNs in Redis could be used to discover mostly simple patterns (often linearly guessable)…

          0 replies 0 retweets 0 likes
          Thanks. Twitter will use this to make your timeline better. Undo
          Undo
        1. ANTIREZ‏ @antirez 25 Sep 2016
          Replying to @fchollet

          example: you train with age, sex, some history from user X, and the outcome of a plan upgrade showing ADs of type Y

          0 replies 0 retweets 0 likes
          Thanks. Twitter will use this to make your timeline better. Undo
          Undo
        3. New conversation
        1. ANTIREZ‏ @antirez 25 Sep 2016
          Replying to @fchollet

          then you ask the network given this user, what AD to show...

          1 reply 0 retweets 0 likes
        2. François Chollet‏Verified account @fchollet 25 Sep 2016
          Replying to @antirez

          looks like it would sometimes be a classification problem and sometime a regression problem. You need support for multiple losses.

          2 replies 0 retweets 0 likes
        3. Show replies
        1. ANTIREZ‏ @antirez 25 Sep 2016
          Replying to @fchollet

          that is… I would like people to use such an API without any understanding of machine learning. A total “black box” :-)

          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