Dementia is a disease that affects the brain and causes deficits in memory and thinking. Alzheimer's disease (AD), which is the most common type of dementia, is a disorder that causes memory loss and disruption of daily life, especially in elderly individuals. Although the treatment of this disease is not yet possible, make provision for can be taken to prevent its progression. Thanks to early diagnosis, treatment can go a long way before permanent damage to the brain occurs. Magnetic resonance (MR) imaging is widely used in the diagnosis of AD, with the analysis of MR images, volumetric changes in the brain can be observed; With these analyzes, it is possible to identify and classify the stages of the disease. It has been observed in the literature review that fast and successful results are obtained in image analysis deep learning methods. In this study, MR images were used and the success of deep learning methods in AD classification was investigated. YOLO v4, a twodimensional convolutional neural network (2D CNN) algorithm, and a threedimensional convolutional neural network model (3D CNN) have been used for AD classification. For the 2D CNN model, the MR data was reduced to 2 dimensions and preprocessed, trained and classified. In the classification results, the 3D CNN model was quite successful compared to the 2D CNN model. While the accuracy value was 68% in the 2D CNN model, this value increased to 88% in the 3D CNN model.