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.

    Adam Marblestone‏ @AdamMarblestone 29 Aug 2019
    • Report Tweet
    • Report NetzDG Violation

    Adam Marblestone Retweeted hardmaru

    If you can make weight-agnostic NNs, maybe you can also make backprop-unnecessary NNs: nets that can learn, with a local or reinforce-based learning rule, what would otherwise need deep exact credit assignment / full gradient to learn. cc @tyrell_turinghttps://twitter.com/hardmaru/status/1166450171372167168 …

    Adam Marblestone added,

    hardmaru @hardmaru
    Replying to @GoogleAI
    Thread with some discussion: https://twitter.com/hardmaru/status/1138600301903003649?s=21 …
    8:02 AM - 29 Aug 2019
    • 9 Retweets
    • 71 Likes
    • Karim Jerbi Tony Zador priya joseph Dan Saunders 𝛁John Giacomo Aldegheri hardmaru Bert Chan Trieu H. Trinh
    7 replies 9 retweets 71 likes
      1. New conversation
      2. Tony Zador‏ @TonyZador 30 Aug 2019
        • Report Tweet
        • Report NetzDG Violation
        Replying to @AdamMarblestone @tyrell_turing

        exactly!

        1 reply 1 retweet 4 likes
      3. Blake Richards‏ @tyrell_turing 30 Aug 2019
        • Report Tweet
        • Report NetzDG Violation
        Replying to @TonyZador @AdamMarblestone

        I just don't buy it... Algs with good credit assignment will likely still way outperform those w/o. But look, I would be happy to be proven wrong. If someone can show good performance on hard tasks using architecture search + non-end-to-end training, cool. Ball's in your court!

        3 replies 0 retweets 13 likes
      4. 20 more replies
      1. New conversation
      2. Blake Richards‏ @tyrell_turing 29 Aug 2019
        • Report Tweet
        • Report NetzDG Violation
        Replying to @AdamMarblestone

        I've read this paper and think it's great. Definitely shows the power of good architecture init. But, I don't think you can avoid cred assignment this way. On the contrary, architecture optimization plus good credit assignment is probably key to human level intelligence.

        3 replies 1 retweet 16 likes
      3. iandanforth‏ @iandanforth 29 Aug 2019
        • Report Tweet
        • Report NetzDG Violation
        Replying to @tyrell_turing @AdamMarblestone

        I think he's looking to contrast local learning rules (which implement credit assignment) with global ones. To which you might reply that local learning rules such as STDP have been and are actively being explored. Primarily by neuro-folk and those in neuromorphic computing. :)

        1 reply 0 retweets 5 likes
      4. 5 more replies
      1. New conversation
      2. hardmaru‏ @hardmaru 30 Aug 2019
        • Report Tweet
        • Report NetzDG Violation
        Replying to @AdamMarblestone @tyrell_turing

        Thanks for the discussion @tyrell_turing @TonyZador !

        1 reply 0 retweets 4 likes
      3. Edgar Bermudez‏ @viajesubmarino 30 Aug 2019
        • Report Tweet
        • Report NetzDG Violation
        Replying to @hardmaru @AdamMarblestone and

        ditto. loved it

        0 replies 0 retweets 2 likes
      4. End of conversation
      1. Dileep George‏ @dileeplearning 31 Aug 2019
        • Report Tweet
        • Report NetzDG Violation
        Replying to @AdamMarblestone @tyrell_turing

        I think for every NN, there is a weight-agnostic circuit that implements the same function. Searching for that circuit, is still 'learning', and likely much more expensive than backprop. The search doesn't seem to be using any local cues.

        0 replies 0 retweets 6 likes
        Thanks. Twitter will use this to make your timeline better. Undo
        Undo
      1. Joscha Bach‏ @Plinz 29 Aug 2019
        • Report Tweet
        • Report NetzDG Violation
        Replying to @AdamMarblestone @tyrell_turing

        That means the network has to learn its own structure for credit assignment. Which is probably how it works in brains. (How do I need to flex to make my model bend in the right way...)

        0 replies 0 retweets 4 likes
        Thanks. Twitter will use this to make your timeline better. Undo
        Undo
      1. Eli Sennesh‏ @EliSennesh 30 Aug 2019
        • Report Tweet
        • Report NetzDG Violation
        Replying to @AdamMarblestone @tyrell_turing

        Without getting into the debate on credit assignment rules, I'd wonder the other way around: how well can we do architecture search/optimization to generate functional forms that are good at approximating the target function regardless of the weights in the linear layers?

        0 replies 0 retweets 3 likes
        Thanks. Twitter will use this to make your timeline better. Undo
        Undo
      1. Mark Kraft‏ @KraftTea 6 Sep 2019
        • Report Tweet
        • Report NetzDG Violation
        Replying to @AdamMarblestone @tyrell_turing

        So, about that petition you signed for @Joi...https://www.newyorker.com/news/news-desk/how-an-elite-university-research-center-concealed-its-relationship-with-jeffrey-epstein …

        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