A Design of Convolutional Neural Network Using ReLU-Based ELM Classifier and Its Application
Jung-Soo Han, Geum‐Bae Cho, Keun-Chang Kwak · 2017
In this paper, we propose a method for combining of CNN(Convolutional Neural Network) with ReLU(Rectified Linear Unit)-based ELM classifier. Basically, the proposed method consists of two phase development. First, CNN is employed to extract features of image database. Next, ReLU-based ELM classifier is used to classify them. The CNN used in this paper uses one of the pre-trained architecture model. The reason is that since hundreds of images have been already learned, it is easy to use for feature extraction and the feature values are classified as input data through the ELM classifier. And we use the activation function that is used to get the optimal output weight in the existing ELM classifier as the ReLU function used to compensate the disadvantage of the existing activation function in the CNN. The experiment is performed by well-known CIFAR-10. The CIFAR-10 database consists of 10 classes, 50000 training images and 10000 test images. The experiment result showed good classification rate and rapid processing time in comparison with conventional machine learning algorithms and ELM itself.