Chris Donahue

@chrisdonahuey

ML/music/audio researcher. Postdoc at Stanford CS. Previously, PhD at UCSD. When do the deadlines stop?

Palo Alto, CA
Vrijeme pridruživanja: siječanj 2012.

Tweetovi

Blokirali ste korisnika/cu @chrisdonahuey

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

  1. Prikvačeni tweet
    15. lis 2018.

    Excited to announce Piano Genie, an intelligent controller that allows anyone to improvise on the piano! This was my internship project at with and . Blog post with more information:

    Prikaži ovu nit
    Poništi
  2. proslijedio/la je Tweet
    4. velj

    "Pop Music Transformer: Generating Music with Rhythm and Harmony" \paper: \demo: \code: ```We propose a new event representation of music that make it easy for models to count the beats```

    Prikaži ovu nit
    Poništi
  3. proslijedio/la je Tweet
    28. sij

    As for the question of whether we will care if stories we like are generated by computer or human (or a combination)... our relationships with art are complex and we can appreciate things for various reasons...

    Prikaži ovu nit
    Poništi
  4. 28. sij

    Some friends of mine set out to tackle the massive challenge of providing a design perspective for AI systems. Their efforts are worth a look!

    Poništi
  5. proslijedio/la je Tweet

    Excited to share this paper w my (philosophy) post-doc . We draw a useful connection b/w the ideal/non-ideal distinction in political philosophy & recent work in fair ML, making clear why recent fair ML can yield misguided policies.

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

    Can we simulate both a user👩‍🦰 and system 🤖 and learn to autocomplete in an unsupervised way? Yes! We frame the autocomplete task as a cooperative communication game. Talk: Dec 14 9:45-10AM (West 118)

    Prikaži ovu nit
    Poništi
  7. proslijedio/la je Tweet
    10. pro 2019.

    Full Schedule and accepted papers for our Creativity Workshop now live on See you on Saturday 14th Dec in West 223-224 🤖🎨

    , , i još njih 5
    Poništi
  8. proslijedio/la je Tweet
    12. pro 2019.

    How can we synthesize programs with functional correctness? 🤖✔️ We release SPoC dataset (18K programs + human-authored pseudocode). Poster #169 at 5-7PM today! SPoC: Search-based Pseudocode to Code (, et al.)

    Prikaži ovu nit
    Poništi
  9. proslijedio/la je Tweet
    8. pro 2019.

    Heading to Vancouver for ! I'll be around all week, check out our workshop on ML for creativity and design on Saturday!

    Poništi
  10. proslijedio/la je Tweet
    3. pro 2019.

    Excited for “Machine Learning in Musical Acoustics” session tomorrow at conference, featuring Bozena Kostek (), , yours truly & more, on topics of MIR, synthesis, imaging, & classification! 1:30-3:35 PST.

    Prikaži ovu nit
    Poništi
  11. proslijedio/la je Tweet

    If a perfect AI generated track drops in the woods and there is no-one around to give it meaning, is it a banger?

    Poništi
  12. proslijedio/la je Tweet
    13. stu 2019.

    I missed this Music-VAE game when it was originally posted. It's fun. In fact I just lost 30 minutes of my day. Great job !

    Poništi
  13. proslijedio/la je Tweet
    12. stu 2019.

    I'm starting a professorship in the CS department at UNC in fall 2020 (!!) and am hiring students! If you're interested in doing a PhD please get in touch. More info here:

    Prikaži ovu nit
    Poništi
  14. proslijedio/la je Tweet
    8. stu 2019.

    Congratulations to & for being the best paper runner up for Designing and Interpreting Probes with Control Tasks . And hearty congratulations to the winner, , of course!

    Poništi
  15. proslijedio/la je Tweet
    Poništi
  16. proslijedio/la je Tweet
    8. stu 2019.

    Whoa! I think this is one of the coolest / most usable things I've seen at .

    Poništi
  17. proslijedio/la je Tweet
    7. stu 2019.
    Poništi
  18. proslijedio/la je Tweet
    7. stu 2019.
    Poništi
  19. proslijedio/la je Tweet
    6. stu 2019.

    Automatically rendering paper piano roll into audio of Debussy playing Debussy by 🤯

    Poništi
  20. proslijedio/la je Tweet
    6. stu 2019.

    Is the first paper author at to drop a new album during a presentation?

    Poništi
  21. proslijedio/la je Tweet
    5. stu 2019.

    This never ends. This year, so far, 15 out of 44 people to attend workshop at (which is still in Canada) have been denied visas. That's 33%. We had all this press last year, they were supposed to help us this year.

    Prikaži ovu nit
    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:

    ·