Evolutionary Convolutional Neural Network: a case study
Most of the state-of-the-art Convolutional Neural Network (CNN) architectures are manually crafted by experts, usually with background knowledge from extent working experience in this research field. Therefore, this manner of designing CNNs is highly limited and many approaches have been developed to try to make this procedure more automatic. This paper presents a case study in tackling the architecture search problem by using a Genetic Algorithm (GA) to optimize an existing CNN Architecture. The proposed methodology uses VGG-16 convolutional blocks as its building blocks and each individual from the GA corresponds to a possible model built from these blocks with varying filter sizes, keeping fixed the original network architecture connections. The selection of the fittest individuals are done according to their weighted F1-Score when training from scratch on the available data. To evaluate the best individual found from the proposed methodology, the performance is compared to a VGG-16 model trained from scratch on the same data.