Convolutional Neural Networks Optimized by Logistic Regression Model
In recent years, convolutional neural networks have been widely used, especially in the field of large scale image processing. This paper mainly introduces the application of two kinds of logistic regression classifier in the convolutional neural network.
- PDF / 581,671 Bytes
- 6 Pages / 439.37 x 666.14 pts Page_size
- 100 Downloads / 205 Views
)
School of Computer Science and Technology, China University of Mining and Technology, Xuzhou 221116, China [email protected]
Abstract. In recent years, convolutional neural networks have been widely used, especially in the field of large scale image processing. This paper mainly intro‐ duces the application of two kinds of logistic regression classifier in the convolu‐ tional neural network. The first classifier is a logistic regression classifier, which is a classifier for two classification problems, but it can also be used for multi-classi‐ fication problems. The second kind of classifier is a multi-classification logistic regression classifier, also known as softmax regression classifier. Two kinds of classifiers have achieved good results in MNIST handwritten digit recognition. Keywords: Convolution neural network · Logistic regression · Softmax regression
1
Introduction
In recent years, since the convolutional neural network is proposed [1], it is widely used in pattern recognition [2], image processing [3], especially achieved good results in the large field of image processing [4]. This paper [5] makes a detailed theoretical analysis of the convolution neural network, then the various classification algorithms and models have been proposed. In the paper [6] proposed the multilayer perceptron as a convolu‐ tional neural network classifier, the paper [7] also used k nearest neighbor algorithm as a convolutional neural network classifier, the paper [8] used support vector machine (SVM) as the convolutional neural network classifier, both of them have achieved good results in the handwritten numeral recognition experiment. The paper [9, 10] mainly introduces the model of linear regression, logistic regression and so on. The paper [11] introduces the softmax regression model, and the detailed formula derivation of the algorithm combined with the back propagation algorithm. The structure of this paper is divided into five parts. The second part mainly intro‐ duces the convolutional neural network structure. The third part mainly introduces two kinds of classification model. The first is a logistic regression model and how to use logistic regression to solve multi classification problem, on the other is the Soft regres‐ sion model. The forth part of the thesis is the experiment and the result analysis. The last part of the paper is the summary.
© IFIP International Federation for Information Processing 2016 Published by Springer International Publishing AG 2016. All Rights Reserved Z. Shi et al. (Eds.): IIP 2016, IFIP AICT 486, pp. 91–96, 2016. DOI: 10.1007/978-3-319-48390-0_10
92
2
B. Yang et al.
Structure of Convolutional Neural Network
Convolutional neural network can be functionally divided into two parts, one is the image feature extraction section, the other part of the classifier. In our experiment, convolutional neural network in the structure can be divided into seven layers including an input layer, convolutional layer C1, sub-sampling layer S2, convolutional layer C3, sub-sampling layer S4, sub-sampling
Data Loading...
