In this section, we will explore different interesting types of CNN architecture. When we say different types of CNN architecture, we basically mean how convolutional and pooling layers are stacked on each other. Additionally, we will learn how many numbers of convolutional, pooling, and fully connected layers are used, what the number of filters and filter sizes are, and more.
CNN architectures
LeNet architecture
The LeNet architecture is one of the classic architectures of a CNN. As shown in the following diagram, the architecture is very simple, and it consists of only seven layers. Out of these seven layers, there are three convolutional layers, two pooling layers, one fully connected layer, and one output layer. It uses...
