MLmediumCnn architectures~15m

Receptive Field and Network Depth in CNNs

Problem

Explain what receptive field means in CNNs, how it grows with network depth, and why VGG-style stacking of 3×3 convolutions is preferred over using a single large kernel like 7×7.

Reference solution

Reference solution available after you attempt the question.

Ready to solve it?

Start a session on Mockbit #81. You'll get graded with specific critique when you submit.