The convolution neural network (CNN) not only has high fault tolerance but also has high computing capacity. The image classification performance of CNN has an important relationship with its network depth. The network depth is deeper, and the fitting ability of CNN is stronger. However, a further increase in the depth of CNN will not improve the accuracy of the network but will produce higher training errors, which will reduce the image classification performance of CNN. In order to solve the above problems, this paper proposes a feature extraction network, AA-ResNet with an adaptive attention mechanism. The residual module of the adaptive attention mechanism is embedded for image classification. It consists of a feature extraction network guided by the pattern, a generator trained in advance, and a complementary network. The feature extraction network guided by the pattern is used to extract different levels of features to describe different aspects of an image. The design of the model effectively uses the image information of the whole level and the local level, and the feature representation ability is enhanced. The whole model is trained as a loss function, which is about a multitask problem and has a specially designed classification, which helps to reduce overfitting and make the model focus on easily confused categories. The experimental results show that the method in this paper performs well in image classification for the relatively simple Cifar-10 dataset, the moderately difficult Caltech-101 dataset, and the Caltech-256 dataset with large differences in object size and location. The fitting speed and accuracy are high.
In order to better assist privately held companies in obtaining commercial credit financing, this article selected 1,000 Chinese privately held companies in the manufacturing industry that went public from 2008 to 2018 and discussed whether a company’s political connections serve as a resource-promoting effect on its commercial credit financing. This article proposed relevant hypotheses based on theoretical analysis and performed the descriptive statistical analysis and Hausman test analysis on all variables based on the unbalanced panel data of public companies when designing the study. Then, this article used a fixed model for regression estimation of the main effects, and the results showed that a company's political connections significantly reduce its possibility of obtaining commercial credit from suppliers. This article further analyzed the regulatory effects of market environmental factors and corporate transparency-related boundary factors and concluded that the process of marketization, the degree of market competition, and the transparency of companies will significantly weaken the inhibiting effect of political connections on commercial credit financing.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.