Designing Convolutional Neural Network Architecture Using Genetic Algorithms

In this paper, genetic algorithm (GA) is used to optimally determine the architecture of a convolutional neural network (CNN) that is used to classify handwritten numbers. The CNN is a class of deep feed-forward network, which have seen major success in the field of visual image analysis. During training, a good CNN architecture is capable of extracting complex features from the given training data; however, at present, there is no standard way to determine the architecture of a CNN. Domain knowledge and human expertise are required in order to design a CNN architecture. Typically architectures, The GA determine the exact architecture of a CNN by evolving the various hyper parameters of the architecture for a given application. The proposed method was tested on the MNIST dataset. The results show that the genetic algorithm is capable of generating successful CNN architectures. The proposed method performs the entire process of architecture generation without any human intervention.