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. 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
    2. 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
    3. 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
    4. 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
    5. 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
    6. Adam Marblestone‏ @AdamMarblestone 25 Aug 2019
      • Report Tweet
      • Report NetzDG Violation
      Replying to @xaqlab @pfau and

      Right. The claim is not just that brain’s dynamics satisfies some arbitrary Euler-Lagrange equations, but that it’s learning dynamics actually corresponds to ongoing optimization during the lifetime of the organism, i.e., brain is itself carrying out an optimization algorithm .

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

      Ok. What about belief propagation? The fixed points are minima of the Bethe free energy, but it doesn't look much like gradient descent.

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

      I think a good example. So we have BP (backprop) and BP (belief propagation). Vicarious seems to like the latter. And people know to search for this in large scale cortical experiments, e.g., many of the IARPA MICRONS proposals centered on this in 2015 or so.

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

      Sure, I mean, I picked that as an example because I know it's Xaq's favorite theory of how cortex works (and Pearl himself was inspired by Rumelhart's speculation about neuroscience).

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

      But I think it also shows that there are so many possible ways that an optimization could be implemented, that it seems inconceivable that we could actually pin down conclusively how the brain is doing it (and there is surely more than one way).

      1 reply 0 retweets 2 likes
      Adam Marblestone‏ @AdamMarblestone 25 Aug 2019
      • Report Tweet
      • Report NetzDG Violation
      Replying to @pfau @xaqlab and

      This may well be right. I certainly can’t say I’m confident it will be figured out with the level of data we have now, plus thinking. But I think BP and BP are two good broad classes of possibility that are not vacuous and tend toward very different predictions when fleshed out.

      7:40 AM - 25 Aug 2019
      1 reply 0 retweets 0 likes
        1. New conversation
        2. David Pfau‏ @pfau 25 Aug 2019
          • Report Tweet
          • Report NetzDG Violation
          Replying to @AdamMarblestone @xaqlab and

          From what I've seen after a decade in the field, people who like deep learning and people who like Bayes can take the same data and claim it supports their favorite type of BP. I'd like to know what the different experimental predictions would be.

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

          But more broadly - and I'd have to think more carefully about this to be sure it's true - I suspect that any fixed point iteration can be reframed as an optimization problem. Which, if true, would take "the brain does optimization" to "neural dynamics converge to a fixed point".

          1 reply 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