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. Gary Marcus‏ @GaryMarcus 24 Dec 2019
      • Report Tweet
      • Report NetzDG Violation

      Gary Marcus Retweeted ప్రదీప్ రెడ్డి / Pradeep Reddy

      four questions for the deep learning community: 1. How would you define deep learning? 2. What if anything are you committed to? 3. What if anything would you say would not count as deep learning? 4. What is the significance of the word "deep", in your definition? #AIDebatehttps://twitter.com/raamana_/status/1209266195678973952 …

      Gary Marcus added,

      ప్రదీప్ రెడ్డి / Pradeep Reddy @raamana_
      this attempted "rebranding" of #DeepLearning seems overly general to me. #AIDebate #MachineLearning pic.twitter.com/6jGd1uQENs
      Show this thread
      40 replies 48 retweets 160 likes
    2. Judea Pearl‏ @yudapearl 24 Dec 2019
      • Report Tweet
      • Report NetzDG Violation
      Replying to @GaryMarcus

      Great questions, @BaryMarcus! May I add a 5th question: What will be lost to AI if we replace the term DL with "super-efficient way of doing regression" or simply "regression"? A lot will be gained, b/c we know so much about what can and cannot be done w/ regression. #Bookofwhy

      6 replies 15 retweets 72 likes
      Joscha Bach‏ @Plinz 24 Dec 2019
      • Report Tweet
      • Report NetzDG Violation
      Replying to @yudapearl @GaryMarcus

      I wish we could drop the ideologies and call it "compositional function approximation".

      10:49 PM - 24 Dec 2019
      • 5 Retweets
      • 30 Likes
      • Yurii Andrieiev Serge Terekhov Sweet Immanence Artur pahlawan tanpa tanda lahir Ben Rubinstein davidad 🎇 MONTREAL.AI marr
      5 replies 5 retweets 30 likes
        1. New conversation
        2. Judea Pearl‏ @yudapearl 24 Dec 2019
          • Report Tweet
          • Report NetzDG Violation
          Replying to @Plinz @GaryMarcus

          And what will be lost if we drop the "compositional" and call it just "function approximation"?? or, God forbid "curve fitting"? (see footnote b in https://ucla.in/2HI2yyx ) #Bookofwhy

          5 replies 2 retweets 18 likes
        3. Joscha Bach‏ @Plinz 24 Dec 2019
          • Report Tweet
          • Report NetzDG Violation
          Replying to @yudapearl @GaryMarcus

          If we drop the ideology, we notice that most deep learners have no compunctions against pasting arbitrary code into their Jupyter notebooks. I understand the animus against fiddling with derivates, but the better algorithm is going to win, no need to push against the others.

          0 replies 0 retweets 3 likes
        4. End of conversation
        1. New conversation
        2. Thomas G. Dietterich‏ @tdietterich 25 Dec 2019
          • Report Tweet
          • Report NetzDG Violation
          Replying to @Plinz @GaryMarcus @yudapearl

          Calling it function approximation doesn’t capture the tremendous flexibility that DL gives the engineer. LSTMs have memory, for example. Capsule networks are doing something like message passing. DL is a new modeling medium and hence needs a new name

          6 replies 2 retweets 31 likes
        3. Joscha Bach‏ @Plinz 25 Dec 2019
          • Report Tweet
          • Report NetzDG Violation
          Replying to @tdietterich @GaryMarcus @yudapearl

          It appears that in each case, we have a message passing network, where every node represents a potentially arbitrary function over the incoming messages, and links are annotated by a vector of parameters that determine the semantics of the message.

          0 replies 0 retweets 1 like
        4. End of conversation
        1. Elias Bareinboim‏ @eliasbareinboim 25 Dec 2019
          • Report Tweet
          • Report NetzDG Violation
          Replying to @Plinz @yudapearl @GaryMarcus

          Composition of functions is still a function; JP's point is not ideological, against composition, functions, or composition of functions It's just about the TYPE OF DATA that one aims to approximate. Causal inference is about DIFFERENT TYPES, hence orthogonal to the technology.

          0 replies 0 retweets 2 likes
          Thanks. Twitter will use this to make your timeline better. Undo
          Undo
        1. Dan STAY THE F&$# HOME Greenberg‏ @titudeadjust 25 Dec 2019
          • Report Tweet
          • Report NetzDG Violation
          Replying to @Plinz @yudapearl @GaryMarcus

          Noooo... You can't do that! Then there would be no "battle" for the media to glom onto, no methodology for inexpert VCs to claim expertise in, etc. We'd have to focus on science, and solutions! The horror!

          0 replies 0 retweets 0 likes
          Thanks. Twitter will use this to make your timeline better. Undo
          Undo
        1. Shamoon Siddiqui {MS, MBA, PhD in progress  🎓}‏ @shamoons 25 Dec 2019
          • Report Tweet
          • Report NetzDG Violation
          Replying to @Plinz @GaryMarcus @yudapearl

          Personally I prefer “mechanized problem solver.”

          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

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