Abstract
As the country’s high-quality talents, college students are an important force in national construction. Evaluating the innovative and entrepreneurial abilities for Chinese students will help promote innovation and entrepreneurship education system and improve the reform of educational system and mechanism of colleges, thereby enhancing the innovation and entrepreneurship abilities of college students and then pushing the country into the ranks of a strong country in human resources and a strong country in talents. This work designs a ResNet-based evaluation method to college innovation and entrepreneurship abilities; the main contributions are as follows. (1) When ResNet performs feature extraction, there are problems of bloated network structure and feature loss. A feature extraction backbone network based on ResNet is proposed. To solve the issue of loss for shallow features in process of feature extraction, a skip architecture is added to fuse the shallow details and spatial information with the deep semantic information. To solve the problem of weak model generalization ability caused by the shallow network, a network stacking strategy is proposed to deepen the network structure. (2) Aiming at the problem that ResNet using single-scale feature prediction cannot effectively utilize multiscale features in the network, a multiscale feature prediction is designed. According to idea of feature pyramid, multiple feature maps with different scales are selected for the improved residual network. It designed a multiscale feature fusion strategy for fusing the selected multiscale feature maps into a feature map and evaluated the innovation and entrepreneurship abilities on the fused feature maps. Finally, comparative experiment proves that the improved feature extraction backbone network and multiscale feature scheme can improve performance accuracy on constructed dataset.
Highlights
In order to verify that the network we designed can effectively evaluate the innovation and entrepreneurship abilities of college students, this work compares the designed method with other methods. e methods compared include decision tree (DT), logistic regression (LR), SVM, and BP network
Researching the innovation as well as entrepreneurship abilities for college students and effectively evaluating innovation and entrepreneurship abilities will help promote the innovation and entrepreneurship education system. is is a necessary condition for a country’s technological development. e ability of college students of innovating and starting business is related to future of a country
The research is on evaluation algorithm of innovation and entrepreneurial ability with ResNet network
Summary
ResNet network to evaluate the innovation and entrepreneurial abilities of college students. Different from the traditional ResNet method, this work will improve the ResNet network from three aspects to further improve accuracy of evaluation for college students’ innovation as well as entrepreneurship capabilities. Is work uses ResNet, which has a relatively small amount of network redundancy and a relatively simple structure, as the basic backbone network. E residual block that composes ResNet is stacked by two convolution kernels with a size of 3 × 3. Residual-1, Residual-2, Residual-3, and Residual-4 in Table 1 are all stacked by multiple residual blocks.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
