[[File:Spiking Neural Network Controlled Virtual Insect Navigate in an Random Terrain.ogv|thumb|The insect is controlled by a spiking neural network to find a target in an unknown terrain.]]
{{main|Artificial neural network}}
'''Spiking neural networks''' ('''SNNs''') fall into the third generation ofare [[artificial neural network]] models,increasingthat themore levelclosely of realism inmimic anatural neural simulationnetworks.<ref name="Maas 1996">{{cite journal|last1=Maass|first1=Wolfgang|title=Networks of spiking neurons: The third generation of neural network models|journal=Neural Networks|volume=10|issue=9|year=1997|pages=1659–1671|issn=0893-6080|doi=10.1016/S0893-6080(97)00011-7}}</ref>{{Clarify|reason=What are the first and second generations?|date=June 2018}} In addition to [[Artificial neuron|neuronal]] and [[Electrical synapse|synaptic]] state, SNNs also incorporate the concept of time into their [[Operating Model|operating model]]. The idea is that [[Artificial neuron|neurons]] in the SNN do not fire at each propagation cycle (as it happens with typical multi-layer [[perceptron|perceptron networks]]), but rather fire only when a [[membrane potential]] – an intrinsic quality of the neuron related to its membrane electrical charge – reaches a specific value. When a neuron fires, it generates a signal which travels to other neurons which, in turn, increase or decrease their potentials in accordance with this signal.
In the context of spiking neural networks, the current activation level (modeled as some [[differential equation]]) is normally considered to be the neuron's state, with incoming spikes pushing this value higher, and then either firing or decaying over time. Various ''coding methods'' exist for interpreting the outgoing ''[[spike train]]'' as a real-value number, either relying on the frequency of spikes, or the timing between spikes, to encode information.
