Classification using spiking neural networks

The functioning of the brain has attracted the interest of people since ancienttimes, how it processes the data has always became a subject of wonder and today,the mystery has still not been solved completely. The major developments in this areaoccurred in the last century with the enhanced knowledge of neuron functioning anddevelopment of more complicated and detailed neuron models. Consequently, the artificialneural networks which are designed as modeling the biological neurons becomea significant area of Artificial Intelligence. Biological neurons transmit information byusing sudden and short voltage increases called action potentials or spikes. SpikingNeural Networks are modeled just like biological neurons and use time informationto fire these spikes. The most important features that distinguish Spiking NeuralNetworks - that are also called third generation neuron models - from the previousgenerations are processing the time information as spikes and keeping multiple connectionsin between consecutive neurons. Eventhough computational complexity andtraining time increases, spiking neural networks are very important because they havegreater biological similarities and solve real world problems. The main purpose of thisthesis is to clear that spiking neural networks can be used in classification problems,back-propagation algorithm can be used to train, in this way, real time datasets canbe classified successfully.