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.

This is the legacy version of twitter.com. We will be shutting it down on June 1, 2020. Please switch to a supported browser, or disable the extension which masks your browser. You can see a list of supported browsers in our Help Center.

  • 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
Plinz's profile
Joscha Bach
Joscha Bach
Joscha Bach
@Plinz

Tweets

Joscha Bach

@Plinz

FOLLOWS YOU. Artificial Intelligence, Cognitive Architectures, Computation. The goal is integrity, not conformity.

San Francisco, CA
bach.ai
Joined April 2009

Tweets

  • © 2020 Twitter
  • About
  • Help Center
  • Terms
  • Privacy policy
  • Imprint
  • 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. Joscha Bach‏ @Plinz 16 Jul 2018
      • Report Tweet
      • Report NetzDG Violation

      Intuition is the part of your knowledge that you cannot test for correctness. Proving correctness requires deriving a very low dimensional representation, so you can apply analytic operators. Most of the functions that a brain approximates cannot be translated into that form.

      6 replies 11 retweets 40 likes
    2. onnlucky 🍀‏ @onnlucky 16 Jul 2018
      • Report Tweet
      • Report NetzDG Violation
      Replying to @Plinz

      Intuition is model-free learned features of our worlds.

      1 reply 0 retweets 1 like
    3. Carlos E. Perez‏ @IntuitMachine 16 Jul 2018
      • Report Tweet
      • Report NetzDG Violation
      Replying to @onnlucky @Plinz

      It's based on an unknown representation that allows use to predict quickly what is possible in our world. It is incorrect to say it is model-free (tabula rasa). We have built in affordances that restrict how we see the world: https://medium.com/intuitionmachine/our-minds-see-and-hear-only-what-we-imagine-dc303056171 … #deeplearning #ai

      2 replies 0 retweets 1 like
    4. onnlucky 🍀‏ @onnlucky 16 Jul 2018
      • Report Tweet
      • Report NetzDG Violation
      Replying to @IntuitMachine @Plinz

      Not model-free as a blank slate, but as in based on statistical/behavioral feature extractors, but not based on causal models. Though I think with one complication, it includes statistically often taken “shortcuts” in causal models to speed up reasoning.

      1 reply 0 retweets 1 like
    5. Carlos E. Perez‏ @IntuitMachine 16 Jul 2018
      • Report Tweet
      • Report NetzDG Violation
      Replying to @onnlucky @Plinz

      I agree, it does not create precise causal models. (Model-free would be an imprecise term) Fuzzy causal models perhaps. Just enough modeling to reason about possibilities. Not statistical because that would be too smart for humans.

      1 reply 0 retweets 0 likes
    6. onnlucky 🍀‏ @onnlucky 16 Jul 2018
      • Report Tweet
      • Report NetzDG Violation
      Replying to @IntuitMachine @Plinz

      For humans, yes, for neural networks, that’s what they do. (See also: https://www.google.nl/amp/s/amp.businessinsider.com/the-incredible-intuition-of-professional-chicken-sexers-2012-3 …) Though also possible it was evolved into neurons by natural selection. Read The Book of Why, then you know what I mean by model-free, it’s very precise.

      1 reply 0 retweets 0 likes
    7. Carlos E. Perez‏ @IntuitMachine 16 Jul 2018
      • Report Tweet
      • Report NetzDG Violation
      Replying to @onnlucky @Plinz

      Well, DeepMind has a position paper "Building Machines that Learn and Think for Themselves" https://arxiv.org/abs/1711.08378v1 … that discusses this model-free notion. I'm well aware of how it relates to intuition.

      1 reply 0 retweets 1 like
    8. onnlucky 🍀‏ @onnlucky 16 Jul 2018
      • Report Tweet
      • Report NetzDG Violation
      Replying to @IntuitMachine @Plinz

      Unfamiliar with that paper. But sounds like the difference between human given models and learned models. A big question is, could current deep learning techniques result in networks that can be said to have causal models, or does learning such require a different technique.

      2 replies 0 retweets 0 likes
      Joscha Bach‏ @Plinz 16 Jul 2018
      • Report Tweet
      • Report NetzDG Violation
      Replying to @onnlucky @IntuitMachine

      IMHO, causal models are simply those that describe a domain as two or more interfacing systems that can affect each other's evolution. There is no reason why DL cannot create such models.

      7:19 AM - 16 Jul 2018 from Berlin, Germany
      1 reply 0 retweets 0 likes
        1. New conversation
        2. onnlucky 🍀‏ @onnlucky 16 Jul 2018
          • Report Tweet
          • Report NetzDG Violation
          Replying to @Plinz @IntuitMachine

          It can learn the external observables, but can it learn the arrow of causation (ie things like Simpson’s paradox, or sunrise because rooster crows or other way around), and/or can it give correct answers when familiar parts are put together in a new way?

          1 reply 0 retweets 0 likes
        3. Carlos E. Perez‏ @IntuitMachine 16 Jul 2018
          • Report Tweet
          • Report NetzDG Violation
          Replying to @onnlucky @Plinz

          Right now, DL is very good at fooling the researcher. See:https://medium.com/intuitionmachine/the-illusion-of-the-ungameable-objective-538a96a53efe …

          0 replies 0 retweets 1 like
        4. 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

        • © 2020 Twitter
        • About
        • Help Center
        • Terms
        • Privacy policy
        • Imprint
        • Cookies
        • Ads info