Data Clustering Via Spiking Neural Networks Through Spike Timing-Dependent Plasticity

摘要

A new spiking-neural-network model for partitioning data into clusters has been developed. The learning process is based on the Spike Timing-Dependent Plasticity rule under the Hebbian Learning framework. With temporally encoded inputs, the synaptic efficiencies of the delays between the pre and postsynaptic spikes can store the information of different data clusters. Various simulation results show that the model is able to perform the data clustering successfully and reach a stable status given enough data samples.