mediumAmazonGoogleMeta

Implement linear regression with gradient descent from scratch.

An ML coding screen that doubles as a calculus check. Interviewers watch whether you can write the MSE gradient without looking it up, explain what the learning rate actually does, and say out loud when you'd just solve the normal equation instead.

Updated Aug 2026 · Grounded in real Forward Deployed Engineer interview loops and written to a senior-engineer editorial bar.

20 answers per topic instead of 10, plus saved progress and bookmarks · no cardor unlock all 559 remaining answers · ₹2,000 / $25

Every answer, concept and course, every paper breakdown, all published video lessons, hands-on FDE Lab missions, Premium PDF guides and companion files, the full practice-test bank and work-sample downloads. Referral Premium excludes guide PDFs and their companion files.

6 months · One payment · No auto-renewal

Study alongside free video lessons.

Keep practising

Next in this trackCompute the edit distance (Levenshtein) between two strings.Premium Next in this trackFind the length of the longest increasing subsequence.Premium Next in this trackCoin change: fewest coins to make an amount.Premium

FEDITOR'S NOTE

The thing that separates a pass from a stall is the gradient. If you derive d/dw of mean squared error live and get the factor of 2/n right, the rest is plumbing. Candidates who memorized 'w -= lr * gradient' but can't say where the gradient comes from get pushed on the derivation until they crack.

DISCUSSION · 0

No comments yet — be the first to share your approach.