While exploring backpropagation and sharing some intuition in [this earlier post]( Seeking feedback on my intuitive understanding of backpropagation from from (from Rumelhart et al., 1986’s paper) - Research - Hugging Face Forums), I decided to write out the full derivation from first principles u can see it in this link :
A Guided Derivation of Backpropagation Algorithm
I’d love to hear your thoughts or feedback and I hope it helps someone who’s starting out the way I did.