Build a small paper CNN and trace how the receptive field grows all the way to the decision.
Proof of success: explain "Pooling, receptive field and CNNs", complete "The Pyramid of Maps" and name the limit of the analogy.
Noé has a 4 × 4 activation map. In each 2 × 2 square, he keeps the maximum value: the map becomes 2 × 2. This max pooling preserves a strong response but forgets its exact position. By alternating convolutions, activations and summaries, a CNN gradually combines a larger area of the image. The receptive field of a unit tells you which input cells can influence its result.
Preview — the rest of the lesson is for enrolled readers.
Your access is tied to your account, not to this link. Sign in with the same email you used in class: your course is waiting, no need to enter the code again.
Sign inNo account yet? Create oneThe first modules of the course are open to everyone. For the rest you have three options: buy this course once and for all, subscribe, or enter the code handed out in class.