Alzheimer’s Disease (AD) is a critical neurodegenerative disorder that causes brain cell degeneration, resulting in enduring cognitive deterioration and presenting a significant health challenge. Due to insufficient knowledge of the underlying causes and the absence of a definitive cure, early detection is very much necessary to inhibit the progression. The complexity of AD, influenced by diverse factors, requires the exploration of advanced neuroimaging techniques, particularly Magnetic Resonance Imaging (MRI), for effective clinical diagnosis. Recently, Deep Learning (DL), a branch of Artificial Intelligence (AI), has proven to be a potent tool in this field, facilitating the automatic extraction of features from medical images for healthcare applications. This paper focuses on leveraging DL, specifically Convolutional Neural Networks (CNNs) along with MRI brain images to categorize AD into four distinct stages: Mild-Demented, Very Mild-Demented, Non-Demented, and Moderate-Demented. CNNs excel in healthcare applications by providing unmatched precision in analyzing medical images. The objective of this work is to achieve maximum accuracy in distinguishing between the mentioned categories. This method provides the information about varying degrees of illness along with the distinction between healthy individuals and those affected by the disease. The combination of CNN and advanced MRI scans is crucial for precise and early detection of AD.