No abstract

Abstract. The Artificial Neural Networks (ANNs) have been used for solving problems in many theoretical and practical areas. Advances on the field of ANNs have derived in Spiking Neural Networks (SNNs); which are considered as the third generation of ANNs. SNNs receive/send the information by timing of events (spikes) instead by the spike rate; as their predecessors do. Although SNNs are capable to solve some functions with fewer neurons than networks of previous generations, there aren't rules to set the architecture of any kind of ANN for solving a specific task; usually the architecture is set empirically based on the designer's experience and the neural network's performance over the problem. Recently, metaheuristic algorithms are being implemented to optimize some aspect on ANNs such as weight, connections and even the architecture. This work proposes a generic framework for automatic construction of Fully-Connected Feed-Forward Spiking Neural Networks through an indirect representation by means of Grammatical Evolution (GE) based on Evolutionary Strategy (ES) algorithm. Two well-known benchmarks datasets of pattern recognition were used for testing the proposal of this paper.

Spiking Neural Networks are considered as the third generation of Artificial Neural Networks, these neural networks naturally process spatio-temporal information. Spiking Neural Networks have been used in several fields and application areas; pattern recognition among them. For dealing with supervised pattern recognition task a gradientdescent based learning rule (Spike-prop) has been developed, however it has some problems like no convergence. To overcome these problems, metaheuristic algorithms such as Evolutionary Strategy have been used. In this work, three variants of the Evolutionary Strategy algorithm are compared for training Spiking Neural Networks. Several well-known benchmark dataset are used to test the capabilities of the algorithms.

No abstract