A Reinforcement Learning Framework for Spiking Networks with Dynamic Synapses
Figure 2
(a) Schematic representation of network setup and simulation. Different-colored input lines indicate nonidentical inputs spike trains. Dashed arrows represent those synaptic connections allowed for learning (details are explained in Section 3.4). (b) Sample of network inputs. (c) Corresponding network output. In both panels, the light gray lines indicate the locations of reference spikes (or ). The blue lines are those correspond to (or ). Note that in the lower panel of (c), the length of (or ) is , where = 5. Both (b) and (c) are adopted from [12].
