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.

For the best Twitter experience, please use Microsoft Edge, or install the Twitter app from Microsoft Store.

  • 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
BlackHC's profile
Andreas Kirsch
Andreas Kirsch
Andreas Kirsch
@BlackHC

Tweets

Andreas Kirsch

@BlackHC

Trained code monkey. DPhil student at @OATML_oxford with @yaringal. @AIMS_oxford @UniofOxford. Former RE @DeepMindAI, SWE @Google. Fellow @nwspk.

Oxford, England
blackhc.net
Joined August 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.

    Andreas Kirsch‏ @BlackHC 16 Jul 2019
    • Report Tweet

    Did you know you can classify MNIST using gzip? 🤓 You can get 45% accuracy on binarized MNIST using class-wise compression and counting bits 🤗 🔥No @PyTorch or @TensorFlow needed 🔥 BASH script and @scikit_learn classifier 👉https://github.com/BlackHC/mnist_by_zip …

    10:02 AM - 16 Jul 2019
    • 95 Retweets
    • 510 Likes
    • sezer Ⓥ Shuyu Lin Limor Gultchin Lei Li Raluca Sandu 🌊🌊🌊 ϕ(lius) Daan Lockhorst Badita Florin On-Device AI Co., Ltd.
    19 replies 95 retweets 510 likes
      1. Andreas Kirsch‏ @BlackHC 17 Jul 2019
        • Report Tweet

        This is getting more attention than expected, so full acknowledgements: thanks to Christopher Mattern (from @DeepMindAI) who mentioned this to me about two years ago over Friday Drinks as fun fact and to @owencm for a random afternoon conversation turning into a tiny project 🎉💕

        0 replies 0 retweets 7 likes
        Show this thread
        Thanks. Twitter will use this to make your timeline better. Undo
        Undo
      1. New conversation
      2. Yann LeCun‏ @ylecun 17 Jul 2019
        • Report Tweet
        Replying to @BlackHC @PyTorch and

        Sure but...45% accuracy is not exactly good. You can get close to 88% with a linear classifier. You can get 95% with nearest-neighbor/L2 distance. No deep learning necessary. But if you want more than 99% without losing your computational shirt, go with ConvNets.

        7 replies 15 retweets 251 likes
      3. Andreas Kirsch‏ @BlackHC 17 Jul 2019
        • Report Tweet
        Replying to @ylecun @PyTorch and

        Thanks! That's true🤗I would not recommend anyone use this classifier in seriousness😇 I was surprised it is working this well at all and better than nearest-neighbor on pixel sums. At best, it's a simple proof-of-concept for information-theoretic approaches😊

        0 replies 0 retweets 11 likes
      4. End of conversation
      1. New conversation
      2. Marc G. Bellemare‏ @marcgbellemare 16 Jul 2019
        • Report Tweet
        Replying to @BlackHC @PyTorch and

        Nice! For completeness, a link to some of the original classification-by-compression work: https://www.cs.waikato.ac.nz/~eibe/pubs/Frank_categorization.full.ps.gz …

        1 reply 2 retweets 14 likes
      3. Andreas Kirsch‏ @BlackHC 17 Jul 2019
        • Report Tweet
        Replying to @marcgbellemare @PyTorch and

        Thanks! I had been looking around a bit for similar papers but haven't found much. It seems well-known in the statistical compression community. Indeed, I have to thank Christopher Mattern (from @DeepMindAI) for mentioning this over drinks three years ago as a fun fact/idea 😊

        0 replies 0 retweets 2 likes
      4. End of conversation
      1. New conversation
      2. Sebastian Raschka‏ @rasbt 17 Jul 2019
        • Report Tweet
        Replying to @BlackHC @PyTorch and

        I was recently wondering about sth similar: you can probably just count the number of pixels (i.e., just do a sum over the pixel values) to classify MNIST images with ~50% accuracy, which isn't too bad.

        1 reply 0 retweets 13 likes
      3. Andreas Kirsch‏ @BlackHC 17 Jul 2019
        • Report Tweet
        Replying to @rasbt @PyTorch and

        Actually, we have tried that 😊You only get 20% accuracy. Zip compression indeed performs significantly better. If you scroll down in the Jupyter Notebook, you can see results for summing on both binarized MNIST and vanilla MNIST. 👉https://github.com/BlackHC/mnist_by_zip/blob/master/MNIST_by_zip.ipynb …

        0 replies 0 retweets 6 likes
      4. End of conversation
      1. New conversation
      2. ok boomer‏ @raxtechbits 17 Jul 2019
        • Report Tweet
        Replying to @BlackHC @PyTorch and

        Yaa, I mean ummm... It is definitely creative. Btw, isn't even like random coins should get like 50 percent accuracy?

        2 replies 1 retweet 2 likes
      3. Andreas Kirsch‏ @BlackHC 18 Jul 2019
        • Report Tweet
        Replying to @raxtechbits @PyTorch and

        Random baseline accuracy is 10% ☺️

        0 replies 0 retweets 3 likes
      4. End of conversation
      1. New conversation
      2. Kenneth Marino‏ @Kenneth_Marino 16 Jul 2019
        • Report Tweet
        Replying to @BlackHC @gokstudio and

        “We are uncertain whether this is an appraisal of zip compression or an indictment of the MNIST dataset.”

        1 reply 1 retweet 5 likes
      3. Nelson Correa‏ @nelscorrea 16 Jul 2019
        • Report Tweet
        Replying to @Kenneth_Marino @BlackHC and

        After 30 years of optimizing on it, the MNIST test set is no longer a test set; it is rather a validation set.

        1 reply 0 retweets 3 likes
      4. 1 more reply

    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