Anna Huang

@huangcza

Google AI Resident on Magenta, working on generative models for music. Previously ML, HCI and music composition at MILA, Harvard, MIT Media Lab and USC

Vrijeme pridruživanja: travanj 2013.

Tweetovi

Blokirali ste korisnika/cu @huangcza

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

  1. Prikvačeni tweet
    13. pro 2018.

    Check out our new blog post on music transformer that generates minute-long pieces that I find myself listening to again! It also generates compelling harmonizations and realizes chord progressions. Which is your favorite? Ours is the Jazz 🎷 👂

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

    Enabling people to converse with chatbots about anything has been a passion of a lifetime for me, and I'm sure of others as well. So I'm very thankful to be able to finally share our results with you all. Hopefully, this will help inform efforts in the area. (1/4)

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

    CfP is out! Abstract Submission, April 10; Final Submission, April 17; Submission of suplementary

    Poništi
  4. proslijedio/la je Tweet
    15. sij

    Differentiable Digital Signal Processing (DDSP)! Fusing classic interpretable DSP with neural networks. ⌨️ Blog: 🎵 Examples: ⏯ Colab: 💻 Code: 📝 Paper: 1/

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

    As promised, we have made the Text-To-Text Transfer Transformer (T5) models much easier to fine-tune for new tasks, and we just released a Colab notebook where you can try it yourself on a free TPU! 👇 (1/3)

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

    We built a really cool machine learning drummer that accompanies your piano in real-time!! This is DrumBot! It’s a web app, so it can come along to your next gig. 🎉 🥁 📝 Blog post: 🎧 Live action:

    Prikaži ovu nit
    Poništi
  7. proslijedio/la je Tweet
    24. stu 2019.

    Very happy to announce: My PhD defense went well, and my thesis.. "Modeling Musical Structure with Artificial Neural Networks" ..is finally online! Download:

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

    Proud of our pals getting a Grammy nomination (Best immersive audio) for their album Chain Tripping. Magenta tools didn't do any of the immersive mixing, but were used extensively throughout the album. Congrats!

    Poništi
  9. 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
  10. proslijedio/la je Tweet
    12. stu 2019.

    Google PAIR is at ! We are recruiting PhD interns and full-time researchers (particularly HCI systems researchers) interested in human-AI interaction. Come talk to me during the Wed. morning coffee break about internships or what life is like in industry research!

    Prikaži ovu nit
    Poništi
  11. proslijedio/la je Tweet
    30. lis 2019.

    We are sharing an open dataset of **15000** cover songs + code of SOTA algorithms + evaluation scripts! Enjoy!!!!

    Poništi
  12. proslijedio/la je Tweet
    30. lis 2019.

    Very excited to present at The Harmonix Set: human annotations of beats, downbeats, and structural segmentation for 912 pop tracks. Download it from: Cool collaboration with the titans from !

    Poništi
  13. proslijedio/la je Tweet
    25. lis 2019.

    Great to see this collaboration between Google researchers & engineers launch, with major improvement to search quality! The work brings together many things we've been working on over the last few years: Transformers, BERT, , TPU pods, ...

    Poništi
  14. proslijedio/la je Tweet
    23. lis 2019.

    New paper! We perform a systematic study of transfer learning for NLP using a unified text-to-text model, then push the limits to achieve SoTA on GLUE, SuperGLUE, CNN/DM, and SQuAD. Paper: Code/models/data/etc: Summary ⬇️ (1/14)

    Prikaži ovu nit
    Poništi
  15. proslijedio/la je Tweet
    11. lis 2019.

    So excited to be a part of this!!! My favourite thing to talk about nowadays is the space that we’re carving for art in the machine learning world, and good news: that’s exactly what i’m speaking about!

    Poništi
  16. proslijedio/la je Tweet
    10. lis 2019.

    PyTorch-Struct (v0.2 ). CRF distributions API, documentation, parsing datasets, new structured models, Tree/Span-LSTM, DGL adapters, and perf. Fun example: RL for learning tree network over math (ListOps)

    Poništi
  17. proslijedio/la je Tweet
    8. lis 2019.

    I used the FFT of the audio of my song Bachbird (a mashup of 's blackbird and 's prelude in C# major) and randomness to construct a journey through the latent space of BigGAN. So it's a GANterpretation of my piece (turn up the sound!). Still very much WIP!

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

    New EMNLP paper “Investigating Multilingual NMT Representation at Scale” w/ , , @caswell_isaac, . We study transfer in massively multilingual NMT from the perspective of representational similarity. Paper: 1/n

    Prikaži ovu nit
    Poništi
  19. proslijedio/la je Tweet
    30. ruj 2019.

    The What-If Tool () has been updated to version 1.4, with tons of new goodness. Just 'pip install witwidget' and check it out in notebooks, or in TensorBoard. Let's dive into some new features... (1/6)

    Prikaži ovu nit
    Poništi
  20. proslijedio/la je Tweet
    4. lis 2019.

    . CS is hiring more assistant professors! Come be my colleague--even the faculty meetings here are fun. :) All areas considered. Apply as soon as you've got your materials together; no need to wait for the last possible second, like I did. ;)

    Poništi
  21. proslijedio/la je Tweet
    4. lis 2019.

    The 19-stroke SPIRAL agent for the oil paint simulator is now available on ! Enjoy 🎨🖌🤖 For usage instructions see The pre-trained snapshot is here:

    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:

    ·