ABHIJIT BALAJI

@balaji_abhijit

AI enthusiast! CS grad student working in computer vision and NLP. I mostly tweet about AI and ML

Vrijeme pridruživanja: veljača 2019.

Tweetovi

Blokirali ste korisnika/cu @balaji_abhijit

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

  1. Prikvačeni tweet
    3. srp 2019.

    Has been an exciting week! Trying to teach CNNs interactively to detect objects in images with 's Prodigy and 's object detection API. Thanks and . Few sample results while teaching Inception-V2 - Faster-RCNN to detect Raccoons!🙃

    Prikaži ovu nit
    Poništi
  2. proslijedio/la je Tweet

    Travelling to Medellín today for ✈️🐍 My keynote will be about the what the future holds for NLP, and how we can enable a new level of developer experience to make the technology available to everyone 🙌

    Poništi
  3. proslijedio/la je Tweet
    3. velj

    Help revolutionize the world with full self-driving by joining us at Tesla Autopilot: It is very hard to find other places where AI expertise makes as much of a difference on as big of a problem.

    Poništi
  4. proslijedio/la je Tweet
    2. velj
    Odgovor korisniku/ci

    A PhD is definitely not required. All that matters is a deep understanding of AI & ability to implement NNs in a way that is actually useful (latter point is what’s truly hard). Don’t care if you even graduated high school.

    Poništi
  5. proslijedio/la je Tweet
    1. velj
    Odgovor korisnicima i sljedećem broju korisnika:

    It's actually a bit different from how Keras had multiple backends. Keras needed to touch quite a big API surface, because it was delegating all the numeric computation. Thinc's shims are just wrappers that have to pass around the inputs, outputs and gradients.

    Poništi
  6. proslijedio/la je Tweet
    28. sij

    Introducing the new Thinc, a refreshing functional take on deep learning! 🔮 Static type checking 🔥 Mix , & ⛓️ Integrated config system 🧮 Extensible backends incl. JAX (experimental) 🧬 Variable-length sequences & more

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

    First, the type system: Thinc was designed for type-checking from day 1, and AFAIK it's the first library to offer detailed support for numpy's API. This helps code readability, gives editor support, and catches some bugs. 2/5

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

    We also have type annotations on the model --- so you can use the types to plan out your model, and again, get type errors if your wiring is wrong. This works especially well with Thinc's functional programming approach. 3/5

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

    Speaking of functional programming...The conceptual model behind Thinc is also something that you might find interesting in itself. It's a different way to program backprop, using callbacks instead of a tape. 4/5

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

    Finally, Thinc also offers some extremely practical features. Have a look at the config system, but also the fact that you can easily wrap other frameworks. Thinc is designed to complement other frameworks, not replace them. 5/5

    Prikaži ovu nit
    Poništi
  11. 28. sij

    Wow! A fresh perspective to implementing deep learning algorithms is out. I cannot believe that I had a small part in it. Thanks . You guys rock!🎊🎉🥳🤯

    Poništi
  12. proslijedio/la je Tweet
    28. sij

    Incredibly proud to release this: a new deep learning library, incorporating lessons we've learned from , and 's FastAPI. Even if you're not looking for new tools, there's lots you might find interesting conceptually. Quick thread: 1/5

    Prikaži ovu nit
    Poništi
  13. proslijedio/la je Tweet
    17. sij

    Super excited to be visiting Colombia next month and giving a keynote at 🐍🎉 Check out the tweet below for my intro video 🙈 and for details on how to get tickets. Hope to see you there!

    Poništi
  14. proslijedio/la je Tweet
    14. sij

    I often meet research scientists interested in open-sourcing their code/research and asking for advice. Here is a thread for you. First: why should you open-source models along with your paper? Because science is a virtuous circle of knowledge sharing not a zero-sum competition

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

    Repository and doc: To install: - Rust: - Python: pip install tokenizers - Node: npm install tokenizers

    Prikaži ovu nit
    Poništi
  16. 8. sij

    It's really important to understand backprop! Most ML/DL libraries abstract this mathematical marvel and makes it feel like magic. I really love the way how forces you to understand backprop. My understanding of backprop deepened after using

    Poništi
  17. proslijedio/la je Tweet
    3. sij

    Let's start out 2020 right by doing something scary. After about a decade of work in my spare time, today I released , a lib for building RL environments where agents solve math problems step-by-step, and a CLI for using pre-trained agents as tutors

    Poništi
  18. 2. sij

    2019 has been an amazing year for me! Shift to Computer Science (MS) from Mechanical Engineering(Bachelors). Interning and working with the amazing . It's amazing and enlightening to work with people whom you lookup to!

    Poništi
  19. proslijedio/la je Tweet
    25. pro 2019.

    As a Christmas present, has made training the algorithm much more memory efficient through lazy loading of the dataset - cf 🎁😎🎄

    Poništi
  20. proslijedio/la je Tweet

    Any users who are also working with audio? I might have something cool for you to beta test soon! 🔊✨

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

    Capture confirmed! After 19 flights to the , Dragon has now delivered over 95,000 pounds of critical supplies to the orbiting laboratory

    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:

    ·