Classification of brainwaves in recordings is of considerable interest to neuroscience and medical communities. Classification techniques used presently depend on the extraction of low-level features from the recordings, which in turn affects the classification performance. To alleviate this problem, this paper proposes an end-to-end approach using Convolutional Neural Network (CNN) which has been shown to detect complex patterns in a signal by exploiting its spatiotemporal nature. The present study uses time and frequency axes for the classification using synthesized Local Field Potential (LFP) data. The results are analyzed and compared with the FFT technique. In all the results, the CNN outperforms the FFT by a significant margin especially when the noise level is high. This study also sheds light on certain signal characteristics affecting network performance.