The 15-Day AI/ML Interview Bootcamp
Day 3 — Linear regression and gradient descent, from a straight line to the loss landscape
Fit a line with least squares, define mean squared error, walk down the loss surface with gradient descent, pick a learning rate that converges, and compare with the closed-form normal equation — machine learning built from scratch, with the gradient descent interview questions.
You book a cab and the app quotes ₹214 before the driver has moved an inch. Nobody typed that number in. Somewhere there's a formula — so much per kilometre, so much per minute, a base charge — and the three numbers in it were found, not written, by a program that looked at a million past rides and slid the numbers around until its guesses stopped being wrong. Today you and I write that program. It's smaller than you think, and the trick at its heart — walking downhill on a surface you can't see — is the same trick that trains every neural network you'll meet in week two. Yesterday's assignmen…
In this lesson
Unlock the rest of The 15-Day AI/ML Interview Bootcamp
Day 3 — Linear regression and gradient descent, from a straight line to the loss landscape is part of the full course. One payment unlocks every lesson, every other course, and every premium article — for life.