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.
  • 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
citnaj's profile
Jason Antic
Jason Antic
Jason Antic
@citnaj

Tweets

Jason Antic

@citnaj

Obsessively pursuing the perfection of image and video colorization/restoration using deep learning. Creator of DeOldify.

Ocean Beach, San Diego
deoldify.ai
Joined January 2010

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. Jason Antic‏ @citnaj 27 Nov 2019
      • Report Tweet
      • Report NetzDG Violation

      Jason Antic Retweeted Smerity

      I saw this paper and immediately dropped what I was doing to read it and got hooked immediately. It’s super interesting, insightful, and FUNNY. I also love his discipline of sticking with a humble desktop to run his experiments- I strongly believe in this.https://twitter.com/Smerity/status/1199529360954257408 …

      Jason Antic added,

      The SHA-RNN is composed of an RNN, pointer based attention, and a “Boom” feed-forward with a sprinkling of layer normalization. The persistent state is the RNN’s hidden state h as well as the memory M concatenated from previous memories. Bake at 200◦F for 16 to 20 hours in a desktop sized oven.
      The attention mechanism within the SHA-RNN is highly computationally efficient. The only matrix multiplication acts on the query. The A block represents scaled dot product attention, a vector-vector operation. The operators {qs, ks, vs} are vectorvector multiplications and thus have minimal overhead. We use a sigmoid to produce {qs, ks}. For vs see Section 6.4.
      Bits Per Character (BPC) onenwik8. The single attention SHA-LSTM has an attention head on the second last layer and hadbatch size 16 due to lower memory use. Directly comparing the head count for LSTM models and Transformer models obviously doesn’tmake sense but neither does comparing zero-headed LSTMs against bajillion headed models and then declaring an entire species dead.
      Smerity @Smerity
      Introducing the SHA-RNN :) - Read alternative history as a research genre - Learn of the terrifying tokenization attack that leaves language models perplexed - Get near SotA results on enwik8 in hours on a lone GPU No Sesame Street or Transformers allowed. https://arxiv.org/abs/1911.11423  pic.twitter.com/RN5TPZ3xWH
      1 reply 20 retweets 131 likes
      Show this thread
    2. Jason Antic‏ @citnaj 27 Nov 2019
      • Report Tweet
      • Report NetzDG Violation

      1/ “Irrational as it seems I didn’t want to use a cluster in the cloud somewhere, watching the dollars leave my bank ac- count as I run various experiments.” That’s exactly how I feel both about doing experiments and even deploying production models.

      1 reply 1 retweet 13 likes
      Show this thread
    3. Jason Antic‏ @citnaj 27 Nov 2019
      • Report Tweet
      • Report NetzDG Violation

      2/ Cloud compute is an easy answer and I think it’s almost assumed by default to be the “right” answer. But, just as an example, I know I wouldn’t experiment like I do if I had to worry about how I was being charged by the hour in the cloud.

      4 replies 0 retweets 10 likes
      Show this thread
    4. Maxime Lenormand‏ @MaxLenormand 28 Nov 2019
      • Report Tweet
      • Report NetzDG Violation
      Replying to @citnaj

      In your view, having your own hardware is better for experimenting than the cloud? Kind of on the fence on which approach to take, but I think the gamer in me will convince the data scientist in me to get some hardware at home

      1 reply 0 retweets 1 like
    5. Jason Antic‏ @citnaj 28 Nov 2019
      • Report Tweet
      • Report NetzDG Violation
      Replying to @MaxLenormand

      I definitely do not regret the decision to get my own hardware. I mostly value it from the psychological/productivity standpoint of feeling free to do whatever I want when I want to.

      1 reply 0 retweets 2 likes
    6. Maxime Lenormand‏ @MaxLenormand 28 Nov 2019
      • Report Tweet
      • Report NetzDG Violation
      Replying to @citnaj

      Do you mind telling what hardware you have? :)

      1 reply 0 retweets 0 likes
      Jason Antic‏ @citnaj 28 Nov 2019
      • Report Tweet
      • Report NetzDG Violation
      Replying to @MaxLenormand

      4 water cooled 1080TIs (for 4 experiments at a time); 16 core/32 thread Threadripper; 128 GB ram; 2TB nvme drive. So it’s a beast and it wasn’t cheap. But I love it and I’m glad I didn’t skimp.

      1:23 AM - 28 Nov 2019
      • 1 Like
      • Louis Maddox
      1 reply 0 retweets 1 like
        1. Maxime Lenormand‏ @MaxLenormand 28 Nov 2019
          • Report Tweet
          • Report NetzDG Violation
          Replying to @citnaj

          Holy crap indeed. I can find a few ideas of what to run on that thing :P

          0 replies 0 retweets 1 like
          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