This network is looking for low-level features such as edges and curves and then building up to more abstract concepts through a series of convolutional layers.

CNN snippet architecture

Figure 1. Illustration of how the CNN is used to solve the MNIST problem.

The CNN snippet consists of the following types of blocks:

2D Convolution. This block is used to detect spatial features in an image.
2D Max pooling. This layer reduces the size of the data. You can say that 2D max pooling is similar to scaling down the size of an image.
Batch normalization. This normalizes all input features to a similar range of values which will speed up learning.
2D Global average pooling. This block is used as an alternative to the Flatten block as it reduces the tensor of the last convolution layer from HxWx128 to a tensor of size 1x1x128.
Dense. This is a densely connected neural network layer.

CNN snippet

CNN snippet architecture

Get the latest updates from Peltarion

Welcome aboard, thanks for signing up