[GL26]

PyTorch already does a huge job at keeping DL not verbose. It captures the complexity to allow you to make a whole GPT model with it, running on your GPU, and keep the code readable. Yes, there are a lot of breaking points, but at some point, DL is supposed to be non trivial, it handles math concepts most people don’t understand. That is why Data Scientists have a job ;)

[sva_]

I mean partial derivatives aren't that complicated if you know normal derivatives, which most people do. And backpropagation isn't too difficult either.

The value of PyTorch lies more in utilizing accelerators like GPUs while offering a nice abstraction. But you can build your own (inefficient) tensor library without too much effort as e.g. Andrej Karpathy has shown in his "NN zero to hero" youtube series.