Optimization of Artificial Neural Network: A Bat Algorithm-Based Approach

Artificial Neural Networks (ANNs) are dominant machine learning tools over the last two decades and are part of almost every computational intelligence task. ANNs have several parameters such as number of hidden layers, number of hidden neurons in each layer, variations in inter-connections between them, etc. Proposing an appropriate architecture for a particular problem while considering all parametric terms is an extensive and significant task. Metaheuristic approaches like particle swarm optimization, ant colony optimization, and cuckoo search algorithm have large contributions in the field of optimization. The main objective of this work is to design a new method that can help in the optimization of ANN architecture. This work takes advantage of the Bat algorithm and combines it with an ANN to find optimal architecture with minimal testing error. The proposed methodology had been tested on two different benchmark datasets and demonstrated results better than other similar methods.