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
AdamMarblestone's profile
Adam Marblestone
Adam Marblestone
Adam Marblestone
@AdamMarblestone

Tweets

Adam Marblestone

@AdamMarblestone

Technologist, Scientist

adammarblestone.org
Joined February 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. Blake Richards‏ @tyrell_turing 24 Aug 2019
      • Report Tweet
      • Report NetzDG Violation
      Replying to @pfau @SussilloDavid and

      Yes, totally. But, that's precisely what we have to change (and what a few groups are working on, including mine): our credit assignment models need to start making physiological predictions that can be falsified. 🙂

      2 replies 0 retweets 6 likes
    2. xaq‏ @xaqlab 25 Aug 2019
      • Report Tweet
      • Report NetzDG Violation
      Replying to @tyrell_turing @pfau and

      Wait, credit assignment = backprop?

      2 replies 0 retweets 1 like
    3. David Pfau‏ @pfau 25 Aug 2019
      • Report Tweet
      • Report NetzDG Violation
      Replying to @xaqlab @tyrell_turing and

      The brain does credit assignment by whatever was cool at NeurIPS 5 years ago.

      1 reply 0 retweets 3 likes
    4. Adam Marblestone‏ @AdamMarblestone 25 Aug 2019
      • Report Tweet
      • Report NetzDG Violation
      Replying to @pfau @xaqlab and

      Let’s add meat to this then, though. What are good options for credit assignment that *don’t* require efficient access to an estimate of the 1st order gradient of an objective function w.r.t. a given synaptic weight deep in a network? Honest question.

      1 reply 1 retweet 3 likes
    5. Adam Marblestone‏ @AdamMarblestone 25 Aug 2019
      • Report Tweet
      • Report NetzDG Violation
      Replying to @AdamMarblestone @pfau and

      (I realize many answers will restrict the architecture or objective fxn greatly, to allow specialized non-backprop ways to get such gradients, which wouldn’t work for general fxn approx in arbitrary net topology. What can you really do with those? What’s the best alternative?)

      2 replies 0 retweets 1 like
    6. Adam Marblestone‏ @AdamMarblestone 25 Aug 2019
      • Report Tweet
      • Report NetzDG Violation
      Replying to @AdamMarblestone @pfau and

      I guess it breaks into 2 cases: 1) you don’t need the gradient, or 2) you do but you have a way to get it that is structurally very different than backprop. For instance this paper gets gradient w/ either backprop or EM (perhaps an example of case #2): https://arxiv.org/abs/1202.3732 

      1 reply 0 retweets 3 likes
    7. David Pfau‏ @pfau 25 Aug 2019
      • Report Tweet
      • Report NetzDG Violation
      Replying to @AdamMarblestone @xaqlab and

      Also I think "the brain minimizes an objective function" is a vacuous statement. All dynamical systems can be reframed as solving a variational problem.

      3 replies 0 retweets 5 likes
    8. xaq‏ @xaqlab 25 Aug 2019
      • Report Tweet
      • Report NetzDG Violation
      Replying to @pfau @AdamMarblestone and

      E.g. a flow field with curl is not the gradient of anything.

      3 replies 0 retweets 4 likes
    9. David Pfau‏ @pfau 25 Aug 2019
      • Report Tweet
      • Report NetzDG Violation
      Replying to @xaqlab @AdamMarblestone and

      That's a narrow definition of minimizing an objective. Hamiltonian dynamics follow a vector field with curl, and that can be reframed as finding a path of least action.

      2 replies 0 retweets 4 likes
    10. Blake Richards‏ @tyrell_turing 25 Aug 2019
      • Report Tweet
      • Report NetzDG Violation
      Replying to @pfau @xaqlab and

      But it doesn't count as credit assignment if it's not normative, i.e. if there isn't a relationship to behaviour getting better in some way. This is not a given. If it was, we wouldn't need backprop in ML.

      1 reply 0 retweets 0 likes
      Adam Marblestone‏ @AdamMarblestone 25 Aug 2019
      • Report Tweet
      • Report NetzDG Violation
      Replying to @tyrell_turing @pfau and

      There is also minimizing in the sense of “being a minimum (stationary point) of” versus minimizing in the sense of “causing to go down over time”.

      7:30 AM - 25 Aug 2019
      • 2 Likes
      • deen-chan xaq
      1 reply 0 retweets 2 likes
        1. New conversation
        2. xaq‏ @xaqlab 25 Aug 2019
          • Report Tweet
          • Report NetzDG Violation
          Replying to @AdamMarblestone @tyrell_turing and

          Good point. When Belief Prop converges, it does so to a local minimum of the Bethe free energy (BFE), but it doesn't follow a gradient on the dynamical variables. And it doesn't always converge either, in which cases it cannot be framed as minimizing the BFE.

          1 reply 0 retweets 1 like
        3. deen-chan‏ @sir_deenicus 25 Aug 2019
          • Report Tweet
          • Report NetzDG Violation
          Replying to @xaqlab @AdamMarblestone and

          The point though, is about getting more optimal behavior and you can get this if the dynamics converge on the typical set of some unknown distribution. Which I suppose answers a way to get learning without optimization (it is also strictly better)

          1 reply 0 retweets 0 likes
        4. 2 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