Numerous nonepileptic paroxysmal events, such as syncopes and psychogenic nonepileptic seizures, may imitate seizures and impede diagnosis. A misdiagnosis can lead to mistreatment, affecting patients’ lives considerably. Electroencephalography is commonly used for diagnosing epilepsy. Although on electroencephalograms (EEGs), epileptiform discharges (ED) specifically indicate epilepsy, only 25%–56% of patients with epilepsy have ED on their first EEG. In this study, we developed a deep convolutional neural network (ConVnet)-based classifier to distinguish EEG between controls and patients with epilepsy without ED. In total, 25 patients with epilepsy without ED in their EEGs and 25 age-matched controls were enrolled. Their EEGs were classified using the deep ConVnet. When the EEG data without overlapping were used, the accuracy, sensitivity, and specificity were 67.00%, 64.00%, and 70.00%, respectively. The performance measures improved when the input EEG data were augmented by overlapping. With 95% EEG data overlapping, the accuracy, sensitivity, and specificity increased to 79.00%, 76.00%, and 82.00%, respectively. Our proposed method could assist neurologists in differentiating between nonepileptic paroxysmal events and epilepsy.