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 26 Dec 2018
      • Report Tweet
      • Report NetzDG Violation
      Replying to @tdietterich @etzioni

      The optimization problem is model discovery. The model itself is data compression. For instance, a mathematical proof compresses statements to axioms. Discovering a proof is finding a computable function that performs that compression.

      2 replies 1 retweet 3 likes
    2. Thomas G. Dietterich‏ @tdietterich 26 Dec 2018
      • Report Tweet
      • Report NetzDG Violation
      Replying to @Plinz @etzioni

      I agree that finding proofs is like playing games, because we can evaluate any proof to determine if it is sound.

      1 reply 0 retweets 0 likes
    3. deen-chan‏ @sir_deenicus 27 Dec 2018
      • Report Tweet
      • Report NetzDG Violation
      Replying to @tdietterich @Plinz @etzioni

      The problem with proofs is you still have the open vs closed domain issue. You aren't selecting from a fixed, clear set of actions per well defined turn. In addition to difficulty in generating valid proofs, evaluation remains an issue because there can be many valid, long paths

      1 reply 0 retweets 1 like
    4. Thomas G. Dietterich‏ @tdietterich 27 Dec 2018
      • Report Tweet
      • Report NetzDG Violation
      Replying to @sir_deenicus @Plinz @etzioni

      I had in mind finding proofs in a formal proof system (e.g., SMT, resolution, etc.). Those are closed worlds once you have formulated the formal claim you wish to prove.

      1 reply 0 retweets 1 like
    5. deen-chan‏ @sir_deenicus 27 Dec 2018
      • Report Tweet
      • Report NetzDG Violation
      Replying to @tdietterich @Plinz @etzioni

      Ah, right. It still seems there'd be difficulty training this. Given a theorem, it must initiate a proof search that emits a proof, unlike games where things can have rounds or be sliced. RL also hard given undecidability of each unfolding tree. Self-play also hard to see

      1 reply 0 retweets 0 likes
    6. Thomas G. Dietterich‏ @tdietterich 27 Dec 2018
      • Report Tweet
      • Report NetzDG Violation
      Replying to @sir_deenicus @Plinz @etzioni

      I was thinking of pure optimization problems, such as Go, where the space of possible moves, the rules of the game, and the definition of winning are all known. In principle this is purely a computational problem. There is no need for machine learning. Proof systems are similar.

      2 replies 0 retweets 1 like
    7. deen-chan‏ @sir_deenicus 27 Dec 2018
      • Report Tweet
      • Report NetzDG Violation
      Replying to @tdietterich @Plinz @etzioni

      I think if this were true, automated theorem proving would not be so difficult. And programming with refinement types backed by Z3 or any SMT would not be so hit and miss and sensitive to slight changes. Go's space is bounded. Proofs aren't bounded.

      1 reply 0 retweets 0 likes
    8. Thomas G. Dietterich‏ @tdietterich 27 Dec 2018
      • Report Tweet
      • Report NetzDG Violation
      Replying to @sir_deenicus @Plinz @etzioni

      My point is not to claim that theorem proving, or go, or chess is computationally easy, but rather that it can be specified as an optimization problem where the computer has the freedom to find solutions previously unknown to humanity. 1/

      1 reply 0 retweets 0 likes
    9. Thomas G. Dietterich‏ @tdietterich 27 Dec 2018
      • Report Tweet
      • Report NetzDG Violation
      Replying to @tdietterich @sir_deenicus and

      The key property of these optimization problems is that the computer can determine for itself whether it has a solution. In contrast, in supervised learning, the computer must generalize from examples, and it cannot tell whether it has found the right answer. 2/

      1 reply 0 retweets 2 likes
    10. Thomas G. Dietterich‏ @tdietterich 27 Dec 2018
      • Report Tweet
      • Report NetzDG Violation
      Replying to @tdietterich @sir_deenicus and

      We can measure the degree of understanding in terms of the size and complexity of the set of queries that the computer can answer based on what it has learned. The set can include counterfactual queries, abstractions, and so on.

      1 reply 0 retweets 0 likes
      Joscha Bach‏ @Plinz 28 Dec 2018
      • Report Tweet
      • Report NetzDG Violation
      Replying to @tdietterich @sir_deenicus @etzioni

      Do you consider it very unlikely that you will see computers that have a unified, integrated world model to which all their models relate, in similar ways as humans do, within your lifetime?

      4:06 AM - 28 Dec 2018 from Leipzig, Germany
      1 reply 0 retweets 0 likes
        1. New conversation
        2. Thomas G. Dietterich‏ @tdietterich 28 Dec 2018
          • Report Tweet
          • Report NetzDG Violation
          Replying to @Plinz @sir_deenicus @etzioni

          I don't think humans have unified, integrated world models. I don't think computers will either.

          1 reply 0 retweets 2 likes
        3. Carlos E. Perez‏ @IntuitMachine 28 Dec 2018
          • Report Tweet
          • Report NetzDG Violation
          Replying to @tdietterich @Plinz and

          Bingo! I agree, the path forward are disjoint world models that are integrated on the fly through a heuristic procedure.

          0 replies 0 retweets 1 like
        4. 6 more replies

      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