newdigital

CNNs are typically complex neural networks whose main applications are in video and image processing, like we saw with GANs in the previous article. However, unlike GANs that are trained in identifying real images and or subjects in the images from fakes, CNNs tend to work more like a classifier in that they split the input data (which is often image pixels) into various subgroups of data whereby each subgroup is meant to capture a key or very important property of the input data. These produced subgroups are often referred to as feature maps.

more...