Sravya Tirukkovalur

@sravsatuluri

ML ex Learning at Loves open source. Having fun with Opinions my own

Vrijeme pridruživanja: veljača 2011.

Tweetovi

Blokirali ste korisnika/cu @sravsatuluri

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

  1. Prikvačeni tweet
    14. lip 2019.

    My talk at "Machine Learning Engineering - A New Yet Not so New Paradigm" is now available to watch:

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

    Retweet if you really really really really really really really really really really really really really really really really really really really really really want more women CEOs.

    Poništi
  3. proslijedio/la je Tweet
    4. sij

    Wow, there is huge revolution on happening right now. More and more competitions are "kernel-only-submisson". Which means you should upload your model to cloud and then all the inference is done in submission kernel with runtime limit. Farewell 100500 models ensembles!

    Poništi
  4. proslijedio/la je Tweet
    29. stu 2019.

    Open-sourcing a community-focused library basically means you'll keep fighting with a bunch of well-intentioned people who want to morph your simple code in a cathedral of complex and smart abstractions. Writing easy-to-read, simple-to-use code is an under-rated skill.

    Prikaži ovu nit
    Poništi
  5. proslijedio/la je Tweet

    Google about implementing BERT to search results: "this is the single biggest ... most positive change we’ve had in the last five years and perhaps one of the biggest since the beginning.” 🔥🔥🔥

    Poništi
  6. 24. lis 2019.

    Protein representation(UniRep) learnt in an unsupervised way just like language models by predicting the next amino acid in the protein sequence. Making downstream protein engineering tasks two orders of magnitude efficient!

    Poništi
  7. proslijedio/la je Tweet
    19. lis 2019.

    So I binge watched on Netflix last night 'cause that is what animal geneticists with an interest in do on a Friday night, & have some thoughts around agricultural applications of genome editing so I wrote a BLOG

    Poništi
  8. 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
  9. proslijedio/la je Tweet
    24. lis 2019.
    Poništi
  10. proslijedio/la je Tweet
    23. lis 2019.

    ✨ Distil-All-The-Things series✨ You ask for it, we do it: today we release **DistilRoBERTa**: 95% of RoBERTa's performance on GLUE, twice as fast and 35% smaller! Available in 🤗Transformers:

    Poništi
  11. proslijedio/la je Tweet
    18. lis 2019.

    We've done a few benchmarks to our 🤗/Transformers library! we compare 10 architectures for inference, with PyTorch and TensorFlow. We further benchmark them with TorchScript and XLA! The results are detailed in the first of a series of blog posts:

    Poništi
  12. proslijedio/la je Tweet

    Did you know that the 2019 winning research from MIT Professors Abhijit Banerjee and Esther Duflo is available online to ANYONE as part of the MITx MicroMasters® program Data, Economics, and Development Policy?

    Poništi
  13. proslijedio/la je Tweet

    It's a special day when my PhD adviser (Kremer) and mentors (Banerjee & Duflo) win the Nobel Prize in economics together. Here's my rapid oped on the prize winners, their work, and the meaning of the prize (links to come):

    Poništi
  14. 15. lis 2019.

    Great to see on-device ML becoming main stream in via voice “Recorder”, “New Assistant” and more

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

    With 180+ papers mentioning 🤗 Transformers and its predecessors, it was high time to put out a real paper that people could cite. 🥳 🎉 With

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

    . discusses how engineering leverages skills from other engineering branches including principles, tools, development and testing practices. :

    Poništi
  17. 9. lis 2019.

    Astrophysicist moving to machine learning roles - still studying latent spaces in a different universe - human universe( fashion style/music/ movie interests)

    Poništi
  18. 8. lis 2019.

    Exciting to see building abstractions in high impact vertical domains( medical in this case)

    Poništi
  19. 3. lis 2019.

    Beyond grateful to have such an awesome team which not only enables you to grow professionally but celebrates your important life event 👧 as a family ! 🥰 🙏🏽

    Poništi
  20. proslijedio/la je Tweet

    Today on 150th Gandhi Jayanti, HIAL launched the movement. Please join us as partners in this innovative crowd-sourcing of goodness for the planet. A unique crowdfunding where you pay not in money, but pledges of behavior change Details on:

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

    I’ve been lucky enough to use Streamlit for a while and it is such an amazing library. Definitely feels like a core part of the ML stack, I can’t wait to see what people build with it!

    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:

    ·