AppliedAIPrep logoAppliedAI/Prep
← Coding & DSA / 66
mediumNVIDIAGoogleMeta

Implement a dropout layer (train and inference) from scratch.

Dropout is five lines, yet most candidates botch two of them: disabling it at inference and scaling the survivors so the expected activation stays constant. Inverted dropout is the convention they want to see.

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

Dropout is five lines, yet most candidates botch two of them: disabling it at inference and scaling the survivors so the expected activation stays constant. Inverted dropout is the convention they want to see.

Unlock the other 750 answers · ₹2,000 / $25Your progress and mastery stay saved · 6 months · one payment · no auto-renew
UP NEXT ON YOUR JOURNEY
Next in this trackLongest Consecutive Sequence in O(n) with a hash set.Next in this trackValidate a Binary Search Tree.Next in this trackCourse Schedule: can you finish all courses given prerequisites (cycle detection)?
DISCUSSION · 0

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