Application of the Levenberg-Marquardt method to the training of spiking neural networks

One of the basic aspects of some neural networks is their attempt to approximate as much as possible their biological counterparts. The goal is to achieve a simple and robust network, easy to comprehend and capable of simulating the human brain at a computational level. This paper presents improvements to the Spikepro algorithm, by introduting a new encoding scheme, and illustrates the application of the Levenberg Marquardt algorithm to this third generation of neural network.