Andreas Kirsch

@BlackHC

Trained code monkey. DPhil student at with . . Former RE , SWE . Fellow .

Oxford, England
Joined August 2009

Tweets

You blocked @BlackHC

Are you sure you want to view these Tweets? Viewing Tweets won't unblock @BlackHC

  1. Pinned Tweet
    25 Jun 2019

    Very happy & proud to share some research in Deep Bayesian Active Learning from , and me at 🎉🎉🎉🤗🤗🤗

    Undo
  2. Jan 30

    That time in the evening when you hate yourself for not installing TexLive earlier on your home workstation ⏳🤦

    Undo
  3. Retweeted

    《バーコーダー》バーコードリーダーのスキャン信号をレジではなく、スピーカーに直接接続することで音を鳴らす。 いま渋谷で巨大レシート版、演奏できます┃┃┃┃_ρ゙

    Show this thread
    Undo
  4. Retweeted
    Jan 21

    if you are wondering what dual numbers are useful for, i wrote up a couple things on em. here's the first: For hyperbolic numbers (also called split complex numbers, among other things), check this out:

    Show this thread
    Undo
  5. Jan 21

    Things to love in the evening: and having swapped argument order (file, obj) vs (obj, file) 😭

    Undo
  6. Jan 20

    When the quick take fails 🤷 also ouch at the subconscious bias 😬

    This Tweet is unavailable.
    Undo
  7. Retweeted
    25 Dec 2019

    Shameless end of year plug for: It's a ~15 page pdf with prompts you fill out to help you reflect on the past year, and plan for the next year. I did it last year and found it to be very helpful, and I will definitely be doing it again for 2019/20.

    Undo
  8. Retweeted
    Jan 18

    There are errors in this post. (1) The likelihood will collapse onto the "good function" as we increase the data size if the data are from the distribution we want to fit, as increasingly fewer bad functions will be consistent with our observations.

    Show this thread
    Undo
  9. Retweeted
    Jan 18

    Edo period cat meme

    Show this thread
    Undo
  10. Retweeted
    Jan 15

    How has helped us advance a new paradigm of agile software development: both experimentation and production ready code within a single workflow! 🌎

    Undo
  11. Jan 14

    Reading Twitter and paper updates this morning and just wanna crawl into a hole. Too much imposter syndrome, too much overwhelm 🙈

    Undo
  12. Retweeted

    The maddening saga of how an Alzheimer’s ‘cabal’ thwarted progress toward a cure for decades via

    Undo
  13. Retweeted

    I wrote this self-contained, 150 line script that trains a ResNet-18 to ~94% accuracy on CIFAR-10. Useful for obtaining a strong baseline with minimal tricks. Uses / Torchvision: 👉

    Undo
  14. Retweeted

    My machine learning education has progressed to the point where I lose sleep tossing around a “brilliant” idea, only to find the next day that it doesn’t actually work. This is great! I talked about this a few years ago:

    Undo
  15. Jan 12
    Undo
  16. Jan 12

    A good blog post overall. Especially that it is important to communicate with team members before rewriting someone's code 😇

    Show this thread
    Undo
  17. Jan 12

    Choose your interfaces wisely but decouple them from your implementations. This is a good pattern that gives you slack in both dimensions to tweak 🎉

    Show this thread
    Undo
  18. Jan 12

    Deduplication of the implemention makes sense though! It allows for better testing and reduces the chance of bugs 💪

    Show this thread
    Undo
  19. Jan 12

    My proposed take is not to change the interface. Keep it as flexible as needed, that is few assumptions, to allow for easy specialization when necessary. Keep your code hackable to be agile 🙏

    Show this thread
    Undo
  20. Jan 12

    The example replaces repetitive code with a neat (👈literally) deduplicated abstraction. The problem with that is that it also tied down the interface to adhering to the chosen abstraction.

    Show this thread
    Undo
  21. Jan 12

    Interesting post that conflates two separate issues: expressive flexible interfaces and code de-duplication. The bit about communication with team members is very important. More details👇

    Show this thread
    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.

    You may also like

    ·