Deep Learning Models Based on Image Classification: A Review

With the development of the big data age, deep learning developed to become having a more complex network structure and more powerful feature learning and feature expression abilities than traditional machine learning methods. The model trained by the deep learning algorithm has made remarkable achievements in many large-scale identification tasks in the field of computer vision since its introduction. This paper first introduces the deep learning, and then the latest model that has been used for image classification by deep learning are reviewed. Finally, all used deep learning models in the literature have been compared to each other in terms of accuracy for the two most challenging datasets CIFAR-10 and CIFAR-100.