Community detection with spiking neural networks for neuromorphic hardware

We present results related to the performance of an algorithm for community detection which incorporates event-driven computation. We de€ne a mapping which takes a graph G to a system of spiking neurons. Using a fully connected spiking neuron system, with both inhibitory and excitatory synaptic connections, the €ring paŠerns of neurons within the same community can be distinguished from €ring paŠerns of neurons in di‚erent communities. On a random graph with 128 vertices and known community structure we show that by using binary decoding and a Hammingdistance based metric, individual communities can be identi€ed from spike train similarities. Using bipolar decoding and €nite rate thresholding, we verify that inhibitory connections prevent the spread of spiking paŠerns.