International Conference on Algorithms, Methodology, Models and Applications in Emerging Technologies (ICAMMAET)

22 / 2016-12-15 11:43:56

Simple Convolution neural network on image classification

Convolution neural network; Deep learning; Image classification

In recent years, deep learning has been used in image classification, object tracking, pose estimation, text detection and recognition, visual saliency detection, action recognition and scene labeling. Among different type of deep neural networks, convolution neural networks has been demonstrated high performance on image classification. In this paper we proposed a simple convolution neural network on image classification. This simple convolution neural network achieves good performance and accuracy and imposes less computational cost. Our experiments are based on benchmarking datasets minist[1]. On the basis of the convolution neural network , we also analyzed different methods of learning rate set and different optimization algorithm of solving the optimal parameters of the influence on image classification. So that we can select the appropriate strategy in image classification