Evolutionary Artificial Neural Network Based on Chemical Reaction Optimization
This is an incremental improvement for researchers and practitioners in machine learning, offering a potentially more efficient training method for neural networks.
The paper tackles the problem of training artificial neural networks by replacing backpropagation with Chemical Reaction Optimization, a population-based metaheuristic, and shows that it outperforms many evolutionary algorithm strategies in simulations.
Evolutionary algorithms (EAs) are very popular tools to design and evolve artificial neural networks (ANNs), especially to train them. These methods have advantages over the conventional backpropagation (BP) method because of their low computational requirement when searching in a large solution space. In this paper, we employ Chemical Reaction Optimization (CRO), a newly developed global optimization method, to replace BP in training neural networks. CRO is a population-based metaheuristics mimicking the transition of molecules and their interactions in a chemical reaction. Simulation results show that CRO outperforms many EA strategies commonly used to train neural networks.