Diabetic Retinopathy (DR) is a disease of the retina which affects patients with diabetes mellitus and is the main cause of blindness. This disease, in which the retinal blood vessels swell, has increasing prevalence among working-age population. The most effective treatment is early detection through regular/manual screenings. Automatic screening methods of DR using images with high accuracy have the potential to assist physicians in evaluating patients earlier, thereby potentially enabling patients to seek timely help from specialists. These methods emphasize on determination of retinal images using appropriate image processing and data mining techniques. In this presentation, we apply deep learning methods to classify a given set of Kaggle images into 5 distinct classes. The classification is carried out through transfer training model and neural networks. Examples will be provided to demonstrate the opportunity and ability of machine learning techniques to help solve this important medical problem.