The loss curve never lies. Here is what backpropagation looks like when it learns.Day 3: visualizing the 1986 paper and pushing to GitHub Day 2 I wrote the code. Today I ran it, plotted everything, and pushed to Gitlab Two charts. One big insight. One honest reflection. If you missApr 3 · 3 min readpapersbyhand.hashnode.dev
I implemented backpropagation in 58 lines of NumPy. No libraries.Yesterday I read the 1986 backpropagation paper. Today I turned it into code. 58 lines of Python. No PyTorch. No TensorFlow. Just NumPy and the raw math from the paper. Here is every line explained soApr 2 · 4 min readpapersbyhand.hashnode.dev
The 4 page paper that powers every AI you useI am reading the classic research papers that built modern AI. One paper per week. I implement everything by hand in Python. No shortcuts. This is Day 1. The paper is called "Learning Representations Apr 1 · 4 min readpapersbyhand.hashnode.dev