Build a Deep Learning Library

4 comments

• amitav1 2 hours ago
  This is cool! This summer I made something similar but in C++. The goal was to build an entire LLM, but I only got to neural networks. GitHub repo here: https://github.com/amitav-krishna/llm-from-scratch. I have a few blogs on this project on my website (https://amitav.net/building-lists.html, https://amitav.net/building-vectors.html, https://amitav.net/building-matrices.html (incomplete)). I hope to finish that series eventually, but some other projects have stolen the spotlight! It probably would have made more sense to write it in Python because I had no C++ experience.
• csantini 1 hour ago
  Did something similar a while back [1], best way to learn neural nets and backprop. Just using Numpy also makes sure you get the math right without having to deal with higher level frameworks or c++ libraries.

  [1] https://github.com/santinic/claudioflow

  [-]
  • butanyways 39 minutes ago
    Its nice! Yeah a lot of the heavy lifting is done by Numpy.
• yunnpp 2 hours ago
  It's alright, but a C version would be even better to fully grasp the implementation details of tensors etc. Shelling out to numpy isn't particularly exciting.
  [-]
  • butanyways 2 hours ago
    I agree! What NumPy is doing is actually quite beautiful. I was thinking of writing a custom c++ backend for this thing. Lets see what happens this year.
    [-]
    • p1esk 0 minutes ago
      If someone is interested in low level tensor implementation details they could benefit from a course/book “let’s build numpy in C”. No need to complicate DL library design discussion with that stuff.
• yazide 1 hour ago
  [flagged]