Hebbian Spike-timing Dependent Self-organization in Pulsed Neural Networks

We present a mechanism of unsupervised competitive learning and development of topology preserving self-organizing maps of spiking neurons. The information encoding is based on the precise timing of single spike events. The work provides a competitive learning algorithm that is based on the relative timing of the preand post-synaptic spikes, local synapse competitions within a single neuron and global competition via lateral connections. Furthermore, we present part of the experimental work on the capability of the suggested mechanism to perform topology preserving mapping and competitive learning. The results show that our model covers the main characteristic behaviour of the standard SOM but uses a computationally more powerful timing-dependent spike encoding.