https://sankethbk.github.io/blog/tags/x/Recent content in X on Sanketh's BlogHugo -- 0.166.0en-usMon, 14 Sep 2026 00:00:00 +0000https://sankethbk.github.io/blog/posts/ml/2026-09-14-1-training-a-2-layer-network-in-numpy/Mon, 14 Sep 2026 00:00:00 +0000https://sankethbk.github.io/blog/posts/ml/2026-09-14-1-training-a-2-layer-network-in-numpy/<h1 id="training-a-2-layer-network-in-numpy-from-scalar-to-vectorized-backprop">Training a 2-Layer Network in NumPy: From Scalar to Vectorized Backprop</h1> <p>The <a href="https://sankethbk.github.io/blog/posts/ml/2026-09-12-3-backpropagation-in-a-fully-connected-network">previous note</a> did the backward pass for a small 2-layer network by hand, one scalar at a time. That is the best way to understand what backprop actually does.</p> <p>This note takes the next step: turn that scalar walk into compact, vectorized NumPy code. The math is unchanged; the only thing that changes is notation. I will introduce every matrix slowly — what its rows and columns mean, where the division by the batch size comes from, and why it is exactly the same algorithm you already did by hand.</p>