Shashank Gupta

@shashank27392

Data Scientist | Interested in Machine Learning | Deep Learning | Information Retrieval | NLP and Social Media analytics. Views expressed are my own.

Vrijeme pridruživanja: ožujak 2015.

Tweetovi

Blokirali ste korisnika/cu @shashank27392

Jeste li sigurni da želite vidjeti te tweetove? Time nećete deblokirati korisnika/cu @shashank27392

  1. Prikvačeni tweet
    25. tra 2017.

    Our WWW work on "Hate Speech Detection in Social Media" featured in Times of India :)

    Poništi
  2. proslijedio/la je Tweet

    By far the best introduction to probabilistic computation i have seen so far: I also love the juxtaposition of code and graphs. By /ht

    Poništi
  3. proslijedio/la je Tweet
    prije 14 sati

    Which products are purchased together can reveal a lot about their relationship. But so can which products are viewed together, but not co-purchased. Our ( & ) new working paper leverages both types of baskets...

    Prikaži ovu nit
    Poništi
  4. proslijedio/la je Tweet

    Trauma. Depression. Anxiety. Poverty. They are all but words. You need to experience them before you understand them. It’s easy to be judgmental. It’s a lot harder to be kind.

    Poništi
  5. proslijedio/la je Tweet
    4. velj

    New episode of the podcast out now Featuring & Dekho, acha laga toh family what’s app group pe daal dena, thoda debate hoga uska mazza lena...

    Poništi
  6. proslijedio/la je Tweet
    4. velj

    Kedro – engineering best-practices library for data and ML pipelines. Comes with project cookiecutter, data access layer, built-in project oversight, Sphinx– and AirFlow integration, etc By

    Poništi
  7. proslijedio/la je Tweet
    3. velj

    104: and talk to us about model distillation, when you try to approximate a large model's decision boundary with a smaller model. After talking about the general area, we dive into DistilBERT.

    Poništi
  8. proslijedio/la je Tweet
    3. velj

    The slides of tutorial are out! You can download them from . *the presentation will take place at 2pm in room A

    Prikaži ovu nit
    Poništi
  9. proslijedio/la je Tweet
    3. velj

    Vespa improvements from January Among other things this includes new tensor functions needed to run BERT models. All of it already released and running in production of course.

    Poništi
  10. proslijedio/la je Tweet
    3. velj
    Poništi
  11. proslijedio/la je Tweet
    2. velj

    Our paper “DySAT: Deep Neural Representation Learning on Dynamic Graphs via Self-Attention Networks” will also be presented in the Graph & Network session on Wed afternoon. Looking forward to meeting you there!

    Poništi
  12. 2. velj

    Good overview of recent advancements in NN based topic models

    Poništi
  13. proslijedio/la je Tweet
    31. sij
    Odgovor korisnicima

    FYI - the write-up is available now at

    Poništi
  14. proslijedio/la je Tweet
    31. sij

    This is a nice package for making pyplot animations more intuitive: All you do is call "camera.snap()" every time you re-do the plot.

    Poništi
  15. 31. sij

    “Tensorflow Extended (TFX) — Towards End to End Machine Learning pipeline — Part 1” by Srivatsan Srinivasan

    Poništi
  16. proslijedio/la je Tweet
    29. sij

    I've always been fascinated by Bayesian Nonparametrics. I struggled to grasp those ideas directly from papers. Today, by chance, I found the best (imo) single reference for anyone interested: A gentle introduction by and Michael Jordan

    Poništi
  17. proslijedio/la je Tweet
    28. sij

    Fun fact: Thinc actually implements all of the practical ideas from my "Let Them Write Code" keynote! 1. Callbacks 2. Function registries 3. Entry points 4. Single-dispatch 🔮 Docs: 🖼 Slides: 📺 Video:

    Poništi
  18. proslijedio/la je Tweet
    29. sij

    Concepts everyone should understand: — Schelling point — Ergodicity — Social signaling — Incentive — Mimetic desire — Randomness — Power law — Cognitive biases — Antifragility — Momentum — Zero-sum game What else?

    Poništi
  19. proslijedio/la je Tweet
    28. sij

    Hidden Markov Models have gotten a bit less love in the age of deep learning, but they are really nifty models that can learn even from tiny datasets. I’ve written a notebook introducing HMMs and showing how to implement them in PyTorch—check it out here:

    Prikaži ovu nit
    Poništi
  20. proslijedio/la je Tweet
    29. sij

    If you want to go beyond the stuff you will learn in MOOCs follow this class from (not an easy class if you take it seriously). Video lectures:

    Poništi
  21. proslijedio/la je Tweet
    27. sij

    There is a livestream for the ! Starting tomorrow :) Looking forward to see the latest research on fairness!

    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:

    ·