This document presents a method for diagnosing Alzheimer's disease using deep learning models to analyze multi-modal medical imaging data, including positron emission tomography (PET) scans and magnetic resonance imaging (MRI) scans. The researchers used data from the Alzheimer's Disease Neuroimaging Initiative to train and test convolutional neural networks and naive Bayes classifiers to classify patients as normal, early mild cognitive impairment, late mild cognitive impairment, or Alzheimer's disease. The results showed the multi-modal approach achieved average classification accuracies of 85%, sensitivities of 82.8%, and specificities of 87.2%, demonstrating the potential of using deep learning on fused imaging data for early and accurate Alzheimer's diagnosis.