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 Oct 20

      François Chollet Retweeted Jan Jitse

      Another great question! Interpolative generalization works as long as the manifold hypothesis applies. This works independently of whether your latent data space is entirely connected, locally connected, or fully discrete.https://twitter.com/etsiJnaJ/status/1450558699714535428 …

      François Chollet added,

      Jan Jitse @etsiJnaJ
      Replying to @etsiJnaJ @fchollet
      1. It seems to be the assumption that the latent manifold is both smooth and connected. What happens if this is not the case? I tend to think that there are reasonable examples of at least non-connected, e.g. if we try to classify 2 type of objects that are very dissimilar.
      3 replies 10 retweets 68 likes
      Show this thread
    2. François Chollet‏Verified account @fchollet Oct 20

      You only need the existence of a manifold (entirely connected) that intercepts your locally-connected areas or discrete points. For instance, predicting y = a * x ** 2 where x is an integer is a discrete problem... that is interpolative in nature.pic.twitter.com/whpII1KkMN

      1 reply 1 retweet 18 likes
      Show this thread
    3. François Chollet‏Verified account @fchollet Oct 20

      In such a case your learned manifold will feature lots of areas that aren't actually meaningful as per the original domain, but that could be interpreted as a continuous extension of the domain (according to the model). Like reals are to integers.

      3 replies 0 retweets 15 likes
      Show this thread
    4. François Chollet‏Verified account @fchollet Oct 20

      This enables you to solve seemingly-discrete problems with deep learning -- as long as they are so structured as to be interpolative, and as long as you can gather a dense sampling of the manifold. The manifold hypothesis must apply.

      1 reply 0 retweets 9 likes
      Show this thread
    5. François Chollet‏Verified account @fchollet Oct 20

      However, when faced with a problem where the manifold hypothesis no longer applies, fitting a differentiable curve via gradient is no longer a good strategy. This is actually *most* of the space of all interesting/useful problems! E.g. most programs that software engineers write.

      2 replies 0 retweets 15 likes
      Show this thread
    6. François Chollet‏Verified account @fchollet Oct 20

      Again, if this is your jam, then this is your book:https://www.manning.com/books/deep-learning-with-python-second-edition?a_aid=keras&a_bid=76564dff …

      1 reply 1 retweet 18 likes
      Show this thread
    7. François Chollet‏Verified account @fchollet Oct 20

      François Chollet Retweeted David Picard

      Ah, but this is incorrect! Virtually all perception problems *do* feature entirely-connected latent manifolds. Natural images are no exception. This is very easy to demonstrate, and something that cinematographers are intimately familiar with...https://twitter.com/david_picard/status/1450697372930088963 …

      François Chollet added,

      David Picard @david_picard
      Replying to @fchollet
      The entire thread makes the assumption there is no disconnectedness. This is not the case for images, eg, face with glasses vs face without glasses. There is no continuous path from one to the other that only contains natural images.
      4 replies 0 retweets 11 likes
      Show this thread
      François Chollet‏Verified account @fchollet Oct 20

      Take a picture of your dog in your backyard, and a picture of your coffee mug on your kitchen table. Unconnected, right? You can't morph one into the other in a continuous fashion, right? Of course you can!

      11:01 AM - 20 Oct 2021
      • 1 Retweet
      • 8 Likes
      • June "Wakalix", 💎 Murky Consequences Lathropa 🍁🍁🍁 Milad Aghajohari Gavin Cawley Shahar SF Zack M. Davis
      1 reply 1 retweet 8 likes
        1. New conversation
        2. François Chollet‏Verified account @fchollet Oct 20

          There's an infinity of ways you could do it, but here's a few trivial ones.

          1 reply 0 retweets 7 likes
          Show this thread
        3. François Chollet‏Verified account @fchollet Oct 20

          1. The handheld camera: just keep the camera rolling as you walk from your kitchen to your backward. Boom, a smooth transition where *every single frame* is extracted from the real world.

          1 reply 0 retweets 14 likes
          Show this thread
        4. François Chollet‏Verified account @fchollet Oct 20

          (be back soon)

          1 reply 0 retweets 5 likes
          Show this thread
        5. François Chollet‏Verified account @fchollet Oct 20

          2. Fade to black: this trick exploits the fact that changing the brightness of an image still gives you a "valid" image. Just fade one frame to black then fade in to the new frame. A bit trivial, I know

          1 reply 0 retweets 7 likes
          Show this thread
        6. François Chollet‏Verified account @fchollet Oct 20

          3. The shared focus: zoom in on one object shared between the two scenes (or background color/texture, e.g. the wood of the table) then zoom out into the new frame.

          1 reply 0 retweets 7 likes
          Show this thread
        7. François Chollet‏Verified account @fchollet Oct 20

          4. A variant of this would be to, say, turn the camera towards the sky you can see from the window, then move it down, and boom, it's your backyard

          1 reply 0 retweets 6 likes
          Show this thread
        8. François Chollet‏Verified account @fchollet Oct 20

          So anyways, the visual world is in fact an entirely connected space (you can go from any valid image to any other valid image via a continuous path where every frame is a valid image). This means that there exists a natural, intrinsic manifold of the visual world.

          2 replies 3 retweets 28 likes
          Show this thread
        9. François Chollet‏Verified account @fchollet Oct 20

          This is true for every perception problem, remarkably. The *physical world* lies on a manifold. And that's what makes deep learning so effective -- its assumptions are a good match to reality.

          1 reply 2 retweets 25 likes
          Show this thread
        10. 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