You do not have to read or understand this section unless you want to!

When it is being trained to recognize fonts, a Scan2CAD neural network is made up of three parts called “layers” –  the Input Layer, the Hidden Layer and the Output Layer. These are summarized in the diagram below.

The word “layer” as used here is standard neural network terminology and is different from the use of the word in the standard CAD sense. Please also note that each layer contains “nodes”. Nodes are different depending on which layer they are on. This is also standard neural network terminology which is why we have retained it here.