This paper explores the potential of deep learning techniques for the early classification of Alzheimer's disease (AD) based on magnetic resonance imaging (MRI) scans. The proposed methodology involves pre-processing the MRI data and extracting a set of features using a convolutional neural network (CNN). The features are then used to train a deep neural network (DNN) classifier to distinguish between normal and AD subjects. Alzheimer’s disease is a disease that causes dementia. An estimated 5.5 million people aged 65 are living with this disease. This is an irreversible, progressive brain disorder, perhaps it is a great deal of effort for early detection. Here, we developed a system of Alzheimer’s disease detection using Convolutional Neural Network (CNN) architecture where Magnetic Resonance Imaging (MRI) images are used as a dataset. The model is trained using this dataset for batch sizes 16, 32 and 64. Here optimizers used are SGD, Adam and RMSprop for EfficientNetB0 and Sequential model which gives the highest accuracy at 96.08% on the test data for EfficientNetB0 and 99.97% for the Sequential model for the detection of AD. The results show that the proposed method achieves high accuracy, sensitivity, and specificity in detecting AD, demonstrating the potential of deep learning techniques for early diagnosis of Alzheimer's disease. This study has important implications for improving the accuracy and reliability of Alzheimer's disease diagnosis, which could lead to earlier treatment and improved outcomes for patients.