The other articles, in order:<p>#1, a single neuron: <a href="https://www.splinter.com.au/2024/03/10/neural-networks-1/" rel="nofollow">https://www.splinter.com.au/2024/03/10/neural-networks-1/</a><p>#2, one neuron's gradient: <a href="https://www.splinter.com.au/2024/03/20/neural-networks-2/" rel="nofollow">https://www.splinter.com.au/2024/03/20/neural-networks-2/</a><p>#3, training: <a href="https://www.splinter.com.au/2024/04/22/neural-networks-3/" rel="nofollow">https://www.splinter.com.au/2024/04/22/neural-networks-3/</a><p>#4, multiple layers and backpropagation: <a href="https://www.splinter.com.au/2024/07/10/neural-networks-4/" rel="nofollow">https://www.splinter.com.au/2024/07/10/neural-networks-4/</a><p>Thanks for your time, I hope it's somewhat informative :)
Hi all, I recently finished writing a series of articles on implementing NNs from scratch, trying to keep it as relatable as possible by demonstrating the maths (math, americans might say) in spreadsheets, pseudocode, and Rust. I really hope someone gets something out of this! Thanks :)