Module 14: Design Development and Certification of Medical Devices

22/11/2023

The Organisation for Professionals in Regulatory Affairs

11

In theory, early filters look for basic features (edges, corners etc) and later filters look at the maps of these features to identify groups of features.

These filters do not need to be designed manually! The same backpropagation process that adjusts weights in a classic neural network will also adjust filters in a convolutional neural network, so the network “learns” the features inherent in the training data.

The Organisation for Professionals in Regulatory Affairs

12

6