In Chapter 7, we looked at a traditional neural network (NN). One of the limitations of a traditional NN is that it is not translation invariant—that is, a cat image on the upper right-hand corner of an image would be treated differently from an image that has a cat in the center of the image. Convolutional neural networks (CNNs) are used to deal with such issues.
Given that a CNN can deal with translation in images, it is considered a lot more useful and CNN architectures are in fact among the current state-of-the-art techniques in object ...
