Skip to content
  • 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
dennybritz's profile
Denny Britz
Denny Britz
Denny Britz
@dennybritz

Tweets

Denny Britz

@dennybritz

Human. Ex-Google Brain, Stanford, Cal. Tweets about ML, startups. Writing at http://wildml.com  and http://dennybritz.com .

Joined January 2008

Tweets

  • © 2019 Twitter
  • About
  • Help Center
  • Terms
  • Privacy policy
  • 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.

    Denny Britz‏ @dennybritz Jan 6

    I hated “idea papers”. High level ideas without experimental evidence were not real science to me. Then I realized that many empirical results are post-rationalized randomness and overffiting. They are not evidence at all. Now I respect idea papers. They are real science.

    5:52 AM - 6 Jan 2019
    • 94 Retweets
    • 544 Likes
    • handol chihiro λndres Mariscal Muni Sreenivas Pydi Stephen  Obonyo Evgeny Pogrebnyak Prabhant Singh Fred Gedling JP Deblonde
    12 replies 94 retweets 544 likes
      1. New conversation
      2. Denny Britz‏ @dennybritz Jan 6

        Someone is putting an idea out there to be tested in a scientific way. They are willing to be proven wrong. They are taking a risk. Someone fitting their theory to their empirical result after the fact takes no risk. Nobody can prove the theory did not come first.

        4 replies 15 retweets 97 likes
        Show this thread
      3. Denny Britz‏ @dennybritz Jan 6

        The former one tries to find causality, which is what we are after. The latter one proves nothing, just correlation.

        5 replies 7 retweets 65 likes
        Show this thread
      4. End of conversation
      1. New conversation
      2. Dr. Manhattan‏ @JohnnyHoncho11 Jan 6
        Replying to @dennybritz

        Argyris Ladder of Inferencepic.twitter.com/n975bgucoz

        1 reply 6 retweets 28 likes
      3. Dr. Manhattan‏ @JohnnyHoncho11 Jan 6
        Replying to @JohnnyHoncho11 @dennybritz

        As well as over fitting, people also disregard data as they apply their belief reenforced bias, "I select the data to observe"

        0 replies 0 retweets 3 likes
      4. End of conversation
      1. Bilal Kartal‏ @bll_krtl Jan 6
        Replying to @dennybritz

        This is so true for RL, the signal to noise ratio gets worse due to scoreboard driven research, too many hyper-parameters, and high compute power.

        0 replies 1 retweet 6 likes
        Thanks. Twitter will use this to make your timeline better. Undo
        Undo
      1. New conversation
      2. Ben Reinhardt‏ @Ben_Reinhardt Jan 6
        Replying to @dennybritz

        As long as the idea is falsifiable. So many idea papers aren't.

        1 reply 0 retweets 3 likes
      3. Joy Chopra‏ @chopra_joy Jan 6
        Replying to @Ben_Reinhardt @dennybritz

        Any example?

        1 reply 0 retweets 0 likes
      4. Tweet unavailable
      5. Ben Reinhardt‏ @Ben_Reinhardt Jan 6

        Einstein's general relativity paper is a good example of a falsifiable idea paper: "if I'm right you should be able to see light bending around the sun."

        1 reply 0 retweets 5 likes
      6. Joy Chopra‏ @chopra_joy Jan 6
        Replying to @Ben_Reinhardt @dennybritz

        I should have been specific. Any example of the non-falsifiable ones? What makes them so. Are the ideas such that we cannnot design experiments to prove/disprove them?

        1 reply 0 retweets 0 likes
      7. Tweet unavailable
      8. Paul Jurczak‏ @pwjurczak Jan 6

        String Theory is an example for today and the near future. Granted, it may change in distant future.

        0 replies 0 retweets 1 like
      9. End of conversation
      1. New conversation
      2. manuel‏ @apmotapinto Jan 6
        Replying to @dennybritz

        What do you mean by "post-rationalized randomness and overfitting"? If an experiment serves the sole purpose of proving something it has serve their purpose and it's not overfitting right?

        1 reply 0 retweets 0 likes
      3. ᴍ:ɴᴏᴠᴧᴇs‏ @marnovo Jan 7
        Replying to @apmotapinto @dennybritz

        Assume the "idea" that 6-sided dice always give a 6 up when thrown. You choose dice until you find biased ones; throw them until you record a streak of 10x consecutive 6s; then present these sole results to support ("prove") the initial claim. A lot of ML papers work like this.

        1 reply 1 retweet 3 likes
      4. manuel‏ @apmotapinto Jan 7
        Replying to @marnovo @dennybritz

        The place where I come from that is called fraud. had no idea.

        1 reply 0 retweets 0 likes
      5. ᴍ:ɴᴏᴠᴧᴇs‏ @marnovo Jan 7
        Replying to @apmotapinto @dennybritz

        My example was obvious, reality less so. I notice sometimes authors themselves don't know that. It's a very heterogenous mix of engineers, data scientists, flavors of PhDs that write papers. Causes are many: lack of training in scientific method or statistics, hidden complexity…

        1 reply 0 retweets 1 like
      6. manuel‏ @apmotapinto Jan 7
        Replying to @marnovo @dennybritz

        Maybe the ocasional promotion lol

        0 replies 0 retweets 1 like
      7. End of conversation
      1. sarath.r.nair‏ @iamsarath Jan 6
        Replying to @dennybritz

        I think you start writing posts back. Better for you and others.😊

        0 replies 0 retweets 2 likes
        Thanks. Twitter will use this to make your timeline better. Undo
        Undo
      1. Gustavo A Rojas‏ @grojas123 Jan 7
        Replying to @dennybritz

        "idea papers" cloud give you a very good questions . Or a very good definition of the problem . That's why many data science and Big data projects fails . The data no talk you need a hypothesis or idea to test .

        0 replies 0 retweets 1 like
        Thanks. Twitter will use this to make your timeline better. Undo
        Undo
      1. pras setya‏ @toya1292 Jan 6
        Replying to @dennybritz

        Idea papers with experimental evidence are the real paper.

        0 replies 0 retweets 1 like
        Thanks. Twitter will use this to make your timeline better. Undo
        Undo
      1. Justin Chen‏ @ch3njust1n Jan 7
        Replying to @dennybritz

        Unfortunate conferences don't accept idea papers or that there arent any conferences for that genre. Are there particular circles you find idea papers written/post more?

        0 replies 0 retweets 0 likes
        Thanks. Twitter will use this to make your timeline better. Undo
        Undo
      1. D S‏ @DSBIC Jan 7
        Replying to @dennybritz

        Eventually every scientist gets to this place if they remain a scientist.

        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

      • © 2019 Twitter
      • About
      • Help Center
      • Terms
      • Privacy policy
      • Cookies
      • Ads info