Live data from Hacker News

Viewing profile — eduardoleao052

eduardoleao052

HN member
Joined
Thu, Mar 28, 2024, 10:17 PM UTC
HN karma
133
Public activity
36 items

About eduardoleao052

Engineering student in the University of Sao Paulo. Interested in the development and application of AI models.

Recent public activity

  1. comment
    Comment #42012800

    Train and deploy Neural Nets and Transformers in the browser with one simple tag!

  2. story
  3. story
  4. comment
    Comment #41020831

    Three months ago I made a post here with an early version of this project, and received some great feedback! One of the most asked features was GPU support, so I added it alongside…

  5. comment
    Comment #41020801

    Thanks for the feedback, glad you liked it! It does, and they work similarly to their PyTorch counterparts. The explanation is on the “Running it Yourself” part of the README.

  6. comment
  7. story
  8. comment
    Comment #39880131

    Thanks for the tip, will look into it! Yes, I think it would always be better to leave a "vanilla" option available.

  9. comment
    Comment #39874387

    That's an interesting idea as well, could definitely see that working in some use cases.

  10. comment
    Comment #39871906

    I’m planning on creating a small article explaining the syntax and the functionalities of the Deep Learning library. I think that could be a useful learning tool, do you think it w…

  11. comment
    Comment #39870564

    I plan on adding Typescript support soon! Thanks for the feedback

  12. comment
    Comment #39867149

    I think that’s it. I’ll probably add that soon

  13. comment
    Comment #39865425

    It would be with some simple tweaks. For instance, the current block does not support Cross-Attention, just Self-Attention.

  14. comment
    Comment #39864408

    Thats true, it’s a limitation of working between these languages. I tried to mitigate it by using clear JSDoc, so that each variable pops up alongside an explanation when calling a…

  15. comment
    Comment #39864223

    Thank you so much for the feedback! I’m open to pull requests, absolutely. And about the article, that’s a great tip, I’ll definitely do that as well.

  16. comment
    Comment #39864177

    Fair enough, I’m currently studying what would be the best option, but I think you are right!

  17. comment
    Comment #39864163

    Really cool implementation. Thanks for the feedback as well!

  18. comment
    Comment #39864129

    Cool! Will take a look

  19. comment
    Comment #39864126

    Thank you! That’s going to help out a lot!

  20. comment
    Comment #39861356

    Thank you for the feedback! If you have any questions or suggestions looking it over tomorrow, I’d love to hear them!

  21. comment
    Comment #39861166

    I had read about this as a possibility, but will definitely look more into it now, thank you for the tip!

  22. comment
    Comment #39861152

    Thanks for the tip! I’ll definitely take a look. Adding GPU support is my next step!

  23. comment
    Comment #39861144

    Adding GPU support soon is absolutely my goal in the future! I think a PyTorch-based JavaScript library could be useful, as PyTorch has been way more dominant than TensorFlow recen…

  24. comment
    Comment #39860513

    I centralized the entire backpropagation around the Operation objects. They store the data about the forward prop in the cache, and serve as the connections in the graphs between t…

  25. comment
    Comment #39860493

    I can try implementing it in the future lol It would surely be a quality of life improvement. But with the current tools, I tried my best to make the syntax as similar as possible …