Re:Neural Networks from Scratch
by shaan7 on Monday October 11, 2021 @11:31AM
(#28829477)
Any recommendations for a 101 book for neural nets for someone who is "just a programmer"? OP's tutorial is quite nice, but I love to read books and find it easier to learn from them.
[ Parent
| on HN ]
Re:Neural Networks from Scratch
by jacobcmarshall on Monday October 11, 2021 @11:50AM
(#28829678)
Deep Learning with Python by Chollet is an excellent beginner resource if you are a hands-on learner.
It starts off with some tutorials using the Keras library, and then gets into the math later on.
By the end of the book, you create multiple different types of neural networks for identifying images, text, and more! I highly recommend it.
I highly recommend http://neuralnetworksanddeeplearning.com/ it’s an online book that has some great code examples built in.
I also found his ‘visual proof’ for neural networks as general function approximators super intuitive.
Fastai has a course: practical deep learning for programmers.
There are also coursera specializations from Andrew Ng at https://deeplearning.ai.
Ng's course is bottom up: Start with the basic math, expand upon it, until you arrive at ML and neural nets.
Fastai is top down: learn to use practical ML with abstractions, and then dig deeper and explain as needed.
I preferred fastai's approach, even though I enjoyed both. Ng's could be a bit too low level and fundamental for what I wanted to learn.
This is a valuable take. Fastai was very frustrating for me because I wanted to understand the internals. I ended up not finishing it, so take my opinion with a grain of salt.
Re:Neural Networks from Scratch
by windsignaling on Monday October 11, 2021 @03:15PM
(#28831872)
I much prefer Andrew Ng's courses as well.
I tried Fast AI, but it seems to be trying too hard to take out the math, which oddly for me (as a STEM grad) makes it much more difficult to understand.
Had to stop when I saw him using Excel spreadsheets to explain convolution.
The Excel spreadsheets is where it all clicked for me. It's not done with some magical library but with simple math being performed on some weights.
There is a book called neural networks from scratch at https://nnfs.io.