Figure 4

(Left) Schematic graph of typical multi-layer neural network where connection weights are shown by varying path width. (Right) Schematic graph of critically synchronized WETCOW inspired shallow neural network, where amplitude weighting factors are again shown by varying path widths, but an additional phase parameter controls the non-planar recurrent paths behavior. The interplay of amplitude-phase synchronization, shown by a non-planarity of a shallow—comprised of a single layer of synchronized loops—neural network, allows more efficient computations, memory requirements, and learning capabilities than multi-layer deep ARCSes of traditional AI/ML neural networks.