Malte Esders

@MalteEsders

PhD in Machine Learning at TU Berlin, interested in Representations for Reinforcement Learning

Vrijeme pridruživanja: lipanj 2019.

Tweetovi

Blokirali ste korisnika/cu @MalteEsders

Jeste li sigurni da želite vidjeti te tweetove? Time nećete deblokirati korisnika/cu @MalteEsders

  1. proslijedio/la je Tweet

    We once again wish to ask all of you for your support. Please, help reach 1 million followers for on Jan 27, 2020. RT, spread the word, let community know about our account where every day we educate about the history of .

    Poništi
  2. proslijedio/la je Tweet
    1. sij

    - finished 7 phds in 4 languages - published 366 papers - completed 8 books - supervised 110 phds - made professor at 22 - married - 7 perfect children - won the World Cup - farted and it came out as diamonds Feel bad about yourself yet?

    Prikaži ovu nit
    Poništi
  3. proslijedio/la je Tweet
    18. pro 2019.

    The state of NLP in 2019. I’m talking with an amazing undergrad who has already published multiple papers on BERT-type things. We are discussing deep into a new idea on pretraining. Me: What would TFIDF do here, as a simple place to start? Him: .... Me: .... Him: What’s TFIDF?

    Prikaži ovu nit
    Poništi
  4. proslijedio/la je Tweet
    17. pro 2019.

    It's finally out! (submitted to LREC) Common Voice: A Massively-Multilingual Speech Corpus

    Prikaži ovu nit
    Poništi
  5. proslijedio/la je Tweet
    17. pro 2019.
    Poništi
  6. proslijedio/la je Tweet

    Coastline Fractal

    Poništi
  7. proslijedio/la je Tweet
    17. ruj 2019.

    Functional RL with Keras and Tensorflow Eager by Eric Liang

    Poništi
  8. proslijedio/la je Tweet
    7. pro 2019.

    Spyder 4.0.0 is here!!! Sorry for the delay, we were fixing some last bugs. We just released this version after three years of hard work! 💪🏻 You can install it following the instructions on

    Poništi
  9. proslijedio/la je Tweet
    7. pro 2019.

    This kind of thing is why the CPU startup I worked for allowed users to change the CPUID: you get huge performance gains from putting GenuineIntel in CPUID(0), but it would be a copyright violation to distribute our CPU with GenuineIntel in the CPUID

    ... The short story is that Intel checks for "Genuine Intel" CPU's when it's numerical library MKL starts executing code. If it find an Intel CPU then it will follow an optimal code path for maximum performance on hardware. If it finds and AMD processor is takes a code path that only optimizes to the old (ancient) SSE2 instruction level ...
    Prikaži ovu nit
    Poništi
  10. proslijedio/la je Tweet
    Poništi
  11. proslijedio/la je Tweet

    can somebody please confirm that this is actually happening and that I'm not just making this up

    Prikaži ovu nit
    Poništi
  12. proslijedio/la je Tweet
    18. stu 2019.

    Few people seem to realize that master is easily built for 's ROCm. For this reason and my own reference I wrote a short how-to at If there is enough interest, I could probably also put up binaries for selected Python versions.

    Prikaži ovu nit
    Poništi
  13. proslijedio/la je Tweet
    18. stu 2019.

    I want to start this trend in academic papers:

    Poništi
  14. proslijedio/la je Tweet

    Overall the ML community at present does not have this problem...

    Poništi
  15. proslijedio/la je Tweet
    19. stu 2019.

    Struggling with crafting the first sentence of your novel? Be comforted by the fact that AI is struggling even more.

    I was playing with my dog, Mark the brown Labrador, and I had forgotten that I was also playing with a dead man.
    Prikaži ovu nit
    Poništi
  16. proslijedio/la je Tweet
    12. stu 2019.

    Have a chat with someone about a result in a paper: "Yeah I get it." Read the paper in detail, multiple times: "Oh yeah, I totally get it!" Write some code to reproduce the result: "Hang on, none of this makes sense?!?"

    Poništi
  17. proslijedio/la je Tweet
    11. stu 2019.

    Hikvision, SenseTime, Face++, etc, companies on the recent U.S. blacklist have been regular sponsors of top computer vision conferences, such as CVPR, ECCV, ICCV. They use those venues to attract talent for developing surveillance technologies. (ie: see )

    Prikaži ovu nit
    Poništi
  18. proslijedio/la je Tweet

    Uyghur / Han ethnicity detection as marketed by a Chinese surveillance company. Yet another example of AI technology being abused as easily as it is used. Preventing abuse requires the right cultural and regulatory frameworks, alongside government support

    Poništi
  19. proslijedio/la je Tweet
    9. stu 2019.

    Some of the most interesting mimicry I’ve ever seen — the wings of this moth (Macrocilix maia) mimic two flies feasting on bird droppings.

    Prikaži ovu nit
    Poništi
  20. proslijedio/la je Tweet
    5. stu 2019.

    When I learned that train_test_split is the most commonly used part of scikit-learn...

    Poništi

Čini se da učitavanje traje već neko vrijeme.

Twitter je možda preopterećen ili ima kratkotrajnih poteškoća u radu. Pokušajte ponovno ili potražite dodatne informacije u odjeljku Status Twittera.

    Možda bi vam se svidjelo i ovo:

    ·