Comment by zelphirkalt

3 years ago

This is what the book has to say (part of a foreword by Peter Norvig):

> Maybe, maybe not. But even if you use a machine learning toolkit like TensorFlow or PyTorch, what you will take away from this book is an appreciation for how the fundamentals work.

10 comments

zelphirkalt

Reply
rg111  3 years ago

I think all serious researchers have implemented core Deep Learning algorithms from scratch. I know I have.

There are two books that do exactly this:

1. Deep Learning from Scratch

2. Data Science from Scratch

In these books, you implement each part of the ML/DL pipeline, from scratch, in Python.

There is also a GitHub project call Minitorch that teaches you the inner workings of a framework like PyTorch.

And then there are several other good resources for exactly this.

What he claims to have as a content is neithet new nor unique.

  • rosetremiere  3 years ago

    How tied are those two books to python? If very much, are there books covering the same content with a different programming language?

    • rg111  3 years ago

      They are aren’t that tied to Python.

      Even if you think so, Python is really an easy language, and you can easily port the code to something else.

      If you already have the basic ideas about the parts of a Neural Network pipeline, you can just search google "implement part-X in Y language", and you will get well written articles/tutorials.

      Many learners/practitioners of Deep Learning, when they have the big enough picture, write an NN training loop in their favorite language(s) and post it online. I remember seeing a good enough "Neural Network in APL" playlist in YT. It implements every piece in APL and gains like 90%+ accuracy in MNIST.

      I also remember seeing articles in Lisp (of course!), C, Elixir, and Clojure.

      I am writing one in J-lang in my free time.

    • bmitc  3 years ago

      I suggest the book Programming Machine Learning. I'm slowly going through the book using another language, and it's easy to translate since the book doesn't use Python's machine learning libraries.

      1 reply →

    • dachryn  3 years ago

      they mostly use numpy (matrix maths library).

      So if you use a library for matrix multiplication, inverse, transpose, ... with a nice syntax, you're good to go.

  • albertzeyer  3 years ago

    What does "from scratch" really mean? You don't reimplement Python itself, or invent a new GPU hardware, a new CUDA including compiler, etc. You don't reimplement the OS. Where do you draw the line?

    Do you reimplement matmul or other basics?

    Do you reimplement auto-diff?

    Maybe PyTorch or TensorFlow using auto-diff is a good "from scratch" basepoint, without using predefined optimizers, or modules/layers, or anything. Just using the low-level math functions, and then auto-diff.