Broad Learning Can Tolerate Noise in Image Recognition

Abstract

In recent years, deep learning has achieved very good results because large amounts of learning data have become easily available due to improvements in computer capabilities and big data. However, it has a problem that the accuracy becomes very bad for strong noise. Therefore, in this study, we compare the classification accuracy of existing mainstream neural networks, including broad learning, convolutional neural network and multilayer perceptron. Then, their performance is verified according to the experimental results by using noise-added MNIST and Fashion MNIST database.