Deep Convolutional Neural Network Ensembles Using ECOC

Deep neural networks have enhanced the performance of decision making systems in many applications, including image understanding, and further gains can be achieved by constructing ensembles. However, designing an ensemble deep is often not very beneficial since time needed to train generally high or gain obtained significant. In this paper, we analyse error correcting output coding (ECOC) framework for ensembles propose different design strategies address accuracy-complexity trade-off. We carry out extensive comparative study between introduced ECOC designs state-of-the-art techniques such as averaging gradient boosting trees. Furthermore, a fusion technique, that shown achieve highest classification performance.