Image Classification with Deep Belief Networks and Improved Gradient Descent

Citations Over Time

Abstract

Image classification mainly uses the classifier to classify the extracted image features. In the traditional image feature extraction, it is difficult to set the appropriate feature patterns for the complex images. Simultaneously, the training algorithm of the classifier also affects the accuracy of image classification. In order to solve these problems, the combination of deep belief networks and the classifier is used for image classification. In the new image classification method, an improved gradient descent method is proposed to train the classifier. Restricted boltzmann machines can be stacked and trained in a greedy manner to form deep belief networks. The deep belief networks are used to extract the features of images and the classifier is used to classify these feature vectors. Compared with other depth learning methods to extract the image features, the deep belief networks can recover the original image using the feature vectors and can guarantee the correctness of the extracted features. Experimental verifications are conducted on MNIST dataset. Experimental results indicate that compared with other classifiers, our approach can get the higher classification accuracy in less time and have superior anti-overfitting ability.

Related Papers

• → A novel deep belief network architecture with interval type-2 fuzzy set based uncertain parameters towards enhanced learning(2023)24 cited
• → Deep Relational Model: A Joint Probabilistic Model with a Hierarchical Structure for Bidirectional Estimation of Image and Labels(2018)2 cited
• → A Deep Belief Network Based Approach for Bearing Fault Diagnosis(2017)
• → A Shallow Neural Network for Simple Image Recognition(2019)