Comparison of Manifold Learning and Deep Learning on Target Classification
Cheng Huang, Wang Hongmei · 2017
With the development of artificial intelligence, classification tasks become more and more popular, but the amount of data is growing dramatically. There are mainly two ways to deal with this problem, one is to reduce the data dimensions directly, the other one is to take advantage of all data through deep learning. In this paper, we will compare these two data processing methods. The first way is to reduce the extracted features' dimensions through manifold learning and then feed into classifiers, and the other way is to deal it directly with deep learning. The experimental results show that deep learning has a better ability than manifold learning in the classification task.