GO TO A SECTION

↑ ↓ to navigate · Enter to openExplore all sections →
FDEInterviews logo
← Machine Learning & Data Science / 43
mediumGoogleScaleMeta

Explain CNN fundamentals (convolution, pooling, parameter sharing). When does classical computer vision still matter?

Convolution and parameter sharing are why a CNN needs a tiny fraction of the weights a dense net would, and why it generalizes across position. The conceptual answer, the feature-hierarchy picture, and the honest take on when a fine-tuned CNN still beats reaching for a giant vision-language model.

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

Convolution and parameter sharing are why a CNN needs a tiny fraction of the weights a dense net would, and why it generalizes across position. The conceptual answer, the feature-hierarchy picture, and the honest take on when a fine-tuned CNN still beats reaching for a giant vision-language model.

20 answers per topic instead of 10, plus saved progress and bookmarks · no cardor unlock all 548 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 trackGradient boosting vs random forests: how does each build trees, the bias-variance behavior, and when to pick which?PremiumNext in this trackExplain SVMs and the kernel trick: what is the margin, when do kernels actually help, and why did SVMs fade for large datasets?PremiumNext in this trackWalk me through Bayes' theorem on a real diagnostic problem: why can a 99%-accurate test still be wrong most of the time it fires?Premium
FEDITOR'S NOTE

The screen is whether the candidate explains parameter sharing as the core efficiency and inductive-bias win, not just 'filters slide over the image.' The reserved follow-up for an FDE is the pragmatic one: 'a customer wants to classify 5000 product photos, what do you actually ship': the strong answer is fine-tune a pretrained CNN/ViT, not train from scratch and not necessarily a multimodal LLM, and knowing why is the applied signal.

DISCUSSION · 0

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