Epilepsy is a common chronic neurological disorder. Epilepsy seizures are the result of the transient and unexpected electrical disturbance of the brain. About fifty million people worldwide have epilepsy, and nearly two out of every three new cases are discovered in developing countries. The detection of epilepsy is possible by analyzing EEG signals. Many researchers have been working on developing a variety of methods for the analysis the EEG signal. In this work, a deep convolutional neural network approach is implemented to detect epilepsy seizure based on EEG signals. Our approach outperforms the previous work used in the analysis of EEG signals, since it eliminates the need for application of preprocessing and dimensionality reduction steps on the data. Experimental results suggest that deep learning networks stand out as a promising approach for neurological diagnosis on EEG data.