Optimized Training for Convolutional Neural Network Using Enhanced Grey Wolf Optimization Algorithm

Convolutional Neural Networks (CNNs) are widely used in image classification tasks and have achieved significant performance. They have different applications with great success, especially in the medical field. The choice of architecture and hyperparameter settings of the CNN, highly influences both accuracy and its convergence speed. The empirical design and optimization of a new CNN architecture require a lot of expertise and can be very time-consuming. This paper proposes an enhanced Grey Wolf Optimization (GWO) algorithm to efficiently explore a defined space of potentially suitable CNN architectures, and simultaneously optimize their hyperparameters. Moreover, we introduce a spatial resolution reduction for a given image processing task, while taking skin cancer detection as a practical application. Through conducted experiments, we have shown that the obtained results are better than other classification methods in terms of accuracy and convergence speed.