A convolutional neural network (CNN) typically consists of multiple layers followed by layers.

A Convolutional Neural Network (CNN) typically consists of multiple convolutional layers followed by pooling layers.

1. Convolutional Layers: These are the major building blocks of CNNs. In these layers, a convolution operation is performed on the input data with the use of a filter or kernel (a small matrix) to then produce a feature map. This operation helps in extracting the high-level features such as edges from the input image.

2. Pooling Layers: These layers follow the convolutional layers. The main function of a pooling layer is to reduce the spatial size (width and height) of the convolved feature. This is to decrease the computational power required to process the data through dimensionality reduction. There are two types of pooling: Max and Average pooling.

After several convolutional and pooling layers, the high-level reasoning in the neural network is done via fully connected layers. A fully connected layer takes all neurons in the previous layer (be it fully connected, pooling, or convolutional) and connects it to every single neuron it has.

Finally, a loss function is applied to measure the inconsistency between predicted and actual labels. The network then backpropagates and adjusts the weights to minimize this loss.

This is a very high-level overview of how a Convolutional Neural Network works.