The progressive decline in cognitive abilities occurred in the early stage of Alzheimer’s disease (AD) is often difficult to be distinguished from the symptoms of mild cognitive impairment (MCI). This study incorporated graph theoretical analysis and machine learning approach to investigate the alterations of brain functional network in AD. Statistical approach demonstrated regions with significantly altered network characteristics, which were also reported to be linked to AD in previous studies. Machine learning approach using TensorFlow also showcases the significant discriminative power of the brain network measures. Future work includes incorporation of other type of network measures, behavior and biochemical assessments, and more complex deep learning models.