Figure 1

A shows three different mathematical formulations implemented. Top equation is original one with which exact bit patterns were learned, as implemented in Scala code. Bottom two equations of A were variations used in more recent work, solving XOR and classifying data. B shows a plot of amount of bit patterns learned by a 2-3-1 DRN architecture as implemented by the top equation in A, showing the effect of the maximum allowed delay per link/connection between two nodes (on x-axis) and the number of bits learned (average and maximum) on the y-axis.