Optimization Analysis of Advanced Mathematical Resources Based on Convolutional Neural Network Algorithm
Gao Junyong, Wang Mingming · 2023
The significance of teaching materials in the domain of higher mathematics is of utmost importance. However, many challenges arise in this context, including the issue of accommodating large classroom sizes, managing substantial workloads, maintaining a rapid pace of instruction, and covering a wide range of knowledge points. The deep neural network technique is insufficient in addressing the challenges associated with teaching resources in advanced mathematics majors, and its assessment lacks rationality. Hence, this study presents a novel convolutional neural network (CNN) technique designed for the purpose of analysing the integration of educational resources. The use of the degree of membership theory is employed to assess resources, and the distribution of teaching resources is adjusted by dividing weights based on indicator needs and minimising interference elements. The degree of membership theory is used to optimise the allocation of teaching resources in higher mathematics, facilitating the development of an optimum resource allocation system and enabling a comprehensive examination of teaching resource outcomes. The convolutional neural network technique effectively distributes educational resources in advanced mathematics, as shown by the MATLAB simulation conducted under certain assessment criteria. The practical utility of the deep neural network technique is inferior to that of other alternatives.