As someone who has read a lot of implementing neural networks from articles, the massive problem with all of them is that they import numpy. You may think that it is silly to reimplement the matrix math but with out that part of the code, you can't easily port it to other languages/microcontrollers/microwaves/badgers.<p>It's a legitimately valid part of machine learning, and its not easy to do for novices.<p>And I need help putting it on my badger damn it!
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.<p>1. <a href="https://www.amazon.com/Make-Your-Own-Neural-Network/dp/1530826608" rel="nofollow">https://www.amazon.com/Make-Your-Own-Neural-Network/dp/15308...</a>
Here's another Neural Network from scratch that I found useful:<p><a href="https://victorzhou.com/blog/intro-to-neural-networks/" rel="nofollow">https://victorzhou.com/blog/intro-to-neural-networks/</a>
This tutorial explained to me at the exact level of detail:<p><a href="https://mattmazur.com/2015/03/17/a-step-by-step-backpropagation-example/" rel="nofollow">https://mattmazur.com/2015/03/17/a-step-by-step-backpropagat...</a><p>It was detailed enough for me to do all the calculations in an excel workbook, 1 complete cycle (forward, backward, and forward with the learned weights)<p><a href="https://1drv.ms/x/s!Ar06sKFtc9d7goR5WQLo-RkB0XvWAA" rel="nofollow">https://1drv.ms/x/s!Ar06sKFtc9d7goR5WQLo-RkB0XvWAA</a><p>Which allowed me to play with the name and factors to understand better how they impact the network as a whole.
Seems like a good intro and I plan to work through it later. I've been learning a lot from Michael Nielsen's book, available at <a href="http://neuralnetworksanddeeplearning.com/index.html" rel="nofollow">http://neuralnetworksanddeeplearning.com/index.html</a>. He doesn't shy away from the underlying math, and his appreciation for it comes through in the writing. Even without a strong math background I was able to punch through the notation and figure things out.
In case it helps, I also had a go at an introductory neural net tutorial which I probably never shared anywhere:<p><a href="https://jsdw.me/posts/neural-nets/" rel="nofollow">https://jsdw.me/posts/neural-nets/</a><p>I found that I had to read a bunch of these things to really grasp them myself.