Make your own neural network
by Tariq Rashid · first published 2016
14mentions
11recommended by
12HN commenters
2016–2024first – last mentioned
92% recommend8% neutral
Why HN recommends it
Gentle, step-by-step introduction that builds a neural network from scratch in Python with NumPy, explaining the calculus simply; well suited to beginners and those who want to demystify ML before using frameworks.
Summarised by Claude from recommending comments
Affiliate links. As an Amazon Associate I earn from qualifying purchases.
You could try looking at Tariq Rashid's video and book: https://www.youtube.com/watch?v=2sevic5Vy4E https://www.amazon.com/Make-Your-Own-Neural-Network-ebook/dp... NN as a concept is hard since it is taught with math, however, I found his book to be easier than any other books I've read as it uses minimal math and down to earth explanations. Since…
on “How to Create a Neural Network in JavaScript [video]” ↗If you think this blog article is lacking, get "Make Your Own Neural Network" by Tariq Rashid[1]. It is way more comprehensive, but still easy to comprehend. It also uses Python to create NN from scratch. 1. https://www.amazon.com/Make-Your-Own-Neural-Network/dp/15308...
on “Build a Neural Network” ↗…https://www.amazon.com/Artificial-Intelligence-Modern-Approa... Note that it is a textbook, with textbook pricing... Another one that I have heard is good for learning neural networks with is: https://www.amazon.com/Make-Your-Own-Neural-Network/dp/15308... There are tons of other resources online - the problem is separating the wheat from the chaff, because some of the stuff is outdated or even considered non-useful. There are many research…
on “Darpa Goes “Meta” with Machine Learning for Machine Learning (2016)” ↗…experience with ML stuff, you might want to start with Andrew Ng's course, which has a small bit on neural networks (MLP and backpropagation), with examples in Matlab/Octave. I found it useful, along with "Make Your Own Neural Network" by Tariq Rashid. Very good intro to coding MLPs directly in Python.
on “Practical Deep Learning for Coders” ↗…think I understand most of the fundamental concepts, and I've been using it quite a lot for creative applications and teaching, and I have to say the best resource I've found for beginners, by far, is "Make Your Own Neural Network" by Tariq Rashid. It starts really from the beginning and it takes you through all the steps of building a NN from zero, with no previous knowledge. really good.
on “TensorFlow, Keras and deep learning, without a PhD” ↗I really recommend the book "Make Your Own Neural Network" by Tariq Rashid for beginners. It uses Python and Numpy. I was able to adapt the code for my own mouse-drawn-symbols recognizer for my AI class project.
on “Building a simple neural net in Java” ↗I'd recommend this short book: https://www.amazon.com/gp/aw/d/B01EER4Z4G/ (Make your own neural network by Tariq Rashid) This one doesn't use any frameworks. The next book by the author (on GANs) uses PyTorch. The math is relatively easy to follow I think. Andrew Ng's courses on Coursera can be viewed…
on “GPT in 60 Lines of NumPy” ↗Disclaimer: I read WAY fewer books in 2023 than what I normally read in a year. So there isn't a big trove to draw from. That said: NON-FICTION: The Blind Watchmaker - Richard Dawkins Make Your Own Neural Network - Tariq Rashid FICTION: Black River Orchard - Chuck Wendig. Just an exceptionally well written horror story. Not necessarily super scary per-se, but well written and enjoyable to read. And I thought…
on “Ask HN: Best Books Read in 2023?” ↗…that breaks down the process step by step. I had my own neural nets working before I touched a framework, and it demystified what would have otherwise seemed like black magic. https://www.amazon.com.au/Make-Your-Own-Neural-Network-ebook...
on “Backpropagation 101 (2020)” ↗…jupyter notebook can do[4]. [0] - https://www.continuum.io/downloads [1] - http://jupyter.readthedocs.io/en/latest/install.html [2] - https://www.codecademy.com/learn/python [3] - https://www.amazon.com/Make-Your-Own-Neural-Network-ebook/dp... [4] - https://try.jupyter.org/
on “GNU Octave” ↗For a good basic intro, this is excellent: https://www.amazon.com/Make-Your-Own-Neural-Network-ebook/dp...
on “A Basic Introduction to Neural Networks (2007)” ↗For anyone who still sees ML as a big of a magic black box, I can't highly recommend this book enough: https://www.amazon.com/Make-Your-Own-Neural-Network-ebook/dp... it does a fantastic job of breaking down the concepts into incredibly straightforward ideas. In fact, the linked article does (IMO) a terrible job at touching on NN by displaying a large…
on “Predict the future with Machine Learning” ↗This book had a really gentle explanation of the required calculus: https://www.amazon.com/Make-Your-Own-Neural-Network-ebook/dp... It also builds some really simple Python code to create a simple (non-"deep", i.e. with just one hidden layer) neural network capable of recognizing human-drawn digits with good accuracy.
on “The Matrix Calculus You Need for Deep Learning” ↗by Tariq Rashid https://www.amazon.com/Make-Your-Own-Neural-Network-ebook/dp/B01EER4Z4G https://www.amazon.com/Make-Your-First-GAN-PyTorch-ebook/dp/B085Z96M9P
on “Ask HN: What were the best books you read this year?” ↗