Search

This paper develops local learning algorithms to solve a classification task with the help of biologically inspired mathematical models of spiking neural networks involving the mechanism of spike‐timing‐dependent plasticity (STDP). The advantages of the models are their simplicity and, hence, the potential ability to be hardware‐implemented in low‐energy‐consuming biomorphic computing devices. The methods developed are based on two key effects observed in neurons with STDP: mean firing rate stabilization and memorizing repeating spike patterns. As the result, two algorithms to solve a classification task with a spiking neural network are proposed: the first based on rate encoding of the input data and the second based on temporal encoding. The accuracy of the algorithms is tested on the benchmark classification tasks of Fisher's Iris and Wisconsin breast cancer, with several combinations of input data normalization and preprocessing. The respective accuracies are 99% and 94% by F1‐score. [ABSTRACT FROM AUTHOR]

Abstract Spiking neural network learning is closely connected to the plasticity mechanism chosen. The aim of this work is to assess, for a network of Leaky Integrate-and-Fire neurons with Spike-Timing-Dependent Plasticity, the influence of STDP constants and input encoding parameters on the accuracy of solving the simple model task of Fisher's Iris classification. Parameter adjustment is performed with a genetic algorithm (GA) on base of NeuroEvolution of Augmenting Topologies (NEAT). The results of the GA with different fitness functions are compared to randomly generating the network parameters. The use of GA is shown to be able to persistently select the network parameters that achieve the highest accuracy for the configuration considered. The network is shown to be more sensitive to its input encoding parameters (encoding rates), than to plasticity constants. [ABSTRACT FROM AUTHOR]