[HN Gopher] Build a Deep Learning Library
       ___________________________________________________________________
        
       Build a Deep Learning Library
        
       Author : butanyways
       Score  : 88 points
       Date   : 2026-01-01 14:53 UTC (8 hours ago)
        
 (HTM) web link (zekcrates.quarto.pub)
 (TXT) w3m dump (zekcrates.quarto.pub)
        
       | amitav1 wrote:
       | 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.
        
       | yunnpp wrote:
       | 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 wrote:
         | 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 wrote:
           | 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.
        
             | butanyways wrote:
             | Yes!!
        
       | csantini wrote:
       | 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 wrote:
         | Its nice! Yeah a lot of the heavy lifting is done by Numpy.
        
       | silentsea90 wrote:
       | Isn't this what Karpathy does as well in the Zero to Hero lecture
       | series on YT? I am sure this is great as well!
        
         | butanyways wrote:
         | If you are asking about the "micrograd" video then yes a little
         | bit. "micrograd" is for scalars and we use tensors in the book.
         | If you are reading the book I would recommend to first complete
         | the series or atleast the "micrograd" video.
        
       | grandimam wrote:
       | This is good. Its well positioned for software engineers to
       | understand DL stuff beyond the frameworks.
        
         | butanyways wrote:
         | thanks!!
        
       | opan wrote:
       | Perhaps obvious to some, but this does not seem to be about
       | learning in the traditional sense, nor a library in the book
       | sense, unfortunately.
        
       ___________________________________________________________________
       (page generated 2026-01-01 23:00 UTC)