TTharunintharunpandya.hashnode.dev·1d ago · 10 min readGradient Descent: Walking Downhill BlindfoldedIn the last post, we built a way to measure exactly how wrong a guess is, using the cost function. Given any w and b, we can now compute a single number that tells us how badly that line fits our data10
TTharunintharunpandya.hashnode.dev·2d ago · 8 min readThe Cost Function: How Wrong Are We, Exactly?Last week, the delivery app on my phone promised my order in 32 minutes. It took 46. I wasn't really annoyed about the food being late. I was annoyed that the model behind that estimate had no way of 10
TTharunintharunpandya.hashnode.dev·3d ago · 10 min readLinear Regression: Fitting a Line Through Chaos A few days ago, I ordered food from an app, and right after placing the order, it showed: "Arriving in 32 minutes." The delivery boy hadn't even picked up the order yet. He hadn't even started riding.10
TTharunintharunpandya.hashnode.dev·5d ago · 7 min readWhat Does It Mean For a Machine to "Learn"?A few weeks back, I was passing through a small town and stopped near a tea stall. I don't drink tea myself, never have, but I ended up standing there for a few minutes just watching the stall owner w10
TTharunintharunpandya.hashnode.dev·Jul 24 · 30 min readEigenvalues and Eigenvectors, Explained for Complete Beginners — The Final Blog in the Linear Algebra for ML SeriesTake a normal photograph and stretch it sideways in an editing app — pull the left and right edges apart, like taffy. Watch what happens to different arrows you could draw on that photo. An arrow poin10
