The Little Learner: A Straight Line to Deep Learning

I'm a huge fan of project based learning like the approach taken in this book. But I'm not sure if it's a good idea to introduce early stage students to Scheme before Python, or deep learning before calculus.

I studied pure math in college, and we were required to take 2 "Computer Science" classes as part of that program. Mainly memorizing textbook algorithms and data structure implementations in Java. I hated programming for years after that, until during graduate school I came up with a project of my own that organically required knowledge of Matlab and later Python. I loved programming after that.

I hope books like this can help new students avoid the trough of disillusionment that can sometimes happen if you're forced to learn a cool subject (like programming) in a very uncool way.

Personally, I would not recommend this book to a young person interested in deep learning and programming (based on the table of contents). I would probably recommend they first learn calculus and use Python to make plots while doing so. Then read Fleuret's "The Little Book of Deep Learning" and try to implement simple models in PyTorch.

The rough part about this book for me is you need to keep it loaded in your working memory the entire time you are reading, and then at the end you realize the thing you actually wanted to read the entire time was in the appendix where they reveal the autodiff/backprop recursion trick.

Then I was like "how the hell". tl;dr gateway drug to Prolog and DCGs. YMMV.

But one things for sure whatever you thought you were gonna get out of this book is gonna be really different than where you end up.

From 2023,

"Pub date: February 21, 2023"