Hands-On Neuroevolution with Python

Visual discrimination experiment setup

In our experiment, during the training of the discriminator ANN, we use the resolution of the visual and target fields fixed at 11 x 11. Thus, the connective CPPN must learn the correct connectivity pattern between the 121 inputs of the visual field and the 121 outputs of the target fields, which results in a total of 14,641 potential connection weights.

The following diagram shows the scheme of the substrate for the discriminator ANN:

The state-space sandwich substrate of the discriminator ANN

The discriminator ANN shown in the diagram has two layers with nodes forming one two-dimensional planar grid ...