In this chapter, we have learned about the basics of CNNs. To begin with, the basic concepts of computer vision were analyzed. Computer vision is the discipline that studies how to enable computers to understand and interpret visual information that's present in images or videos. This also deals with the analysis of numerical images.
Then, the architecture of convolutional network models was explored. A CNN consists of a series of layers such as input, convolutional, ReLU, pool, and fully connected layers. Each identify as a level of the CNN. The convolutional layer is the main level of the network. Its goal is to identify patterns, such as curves, angles, circumferences, or squares that have been depicted in an image with high accuracy. The ReLU layer aims to erase negative values that have been obtained in previous levels, and it is usually placed after convolutional...
