Image Classification using Fast Learning Convolutional Neural Networks

In this paper, we propose an image classification method for improving the learning speed of convolutional neural networks (CNN). Although CNN is widely used in multiclass image classification datasets, the learning speed remains slow for large amounts of data. Therefore, we attempted to improve the learning speed by applying an extreme learning machine (ELM). We propose a learning method combining a network of CNN with this ELM. First, we use an orthogonal bipolar vector (OBV) for studying different types of neural networks. After learning a limited epoch used in the CNN, we determine the output of the neural network using the ELM. To evaluate the performance, we compared the learning speed and classification rate of conventional CNN against the proposed method. Experimental results show that the proposed algorithm has a faster learning curve than the existing algorithm.