Figure 5.
Dynamic dataset of N-MNIST. (A) Each sub-picture shows a 10ms-width spike train during the saccades. (B) Spike train is generated by moving the dynamic vision sensor (DVS) in turn toward the direction of 1, 2, and 3. (C) Spatio-temporal representation of the spike train from digit 0 (Orchard et al., 2015)where the upper one and lower one denote the on-events and off-events, respectively.