Research on the Evaluation Model of Educational Management Theory Based on Data Mining from the Perspective of Neural Network

Abstract

The improvement of the theoretical quality of education management is an indispensable part of a country’s education modernization. However, the existing research on the evaluation of educational management theory is still relatively small, and there is a lack of scientific educational management theory evaluation model. Designing a comprehensive and accurate educational management theory evaluation model has important theoretical value and practical significance. It is possible to process a lot of information in parallel using the artificial neural network method. By optimizing the artificial neural network, data mining of characteristic information data can be realized. Therefore, this paper uses neural network to conduct data mining on education management theory and conduct a comprehensive system evaluation of education management theory. At the same time, the traditional BP algorithm is improved. To train a neural network with large amounts of data, the BP algorithm uses a lot of gradient calculation, which takes a long time and often results in training going to extremes in the local area. BP neural networks are trained using the particle swarm optimization algorithm, and the backward propagation process in the BP algorithm is replaced with particle swarm iteration. To improve algorithm execution efficiency and speed up neural network training, a large number of gradient operations can be avoided. This can help overcome the limitations of the BP algorithm when dealing with large amounts of data. The improved BP algorithm is applied to the evaluation system of education management theory, and the quality evaluation prediction of management education theory is realized.

Quality Assessment Method of Information Model Reform of Higher Mathematics Education Based on Big Data

“…Based on modern statistical theory, they belong to the category of data mining and obtain better results in higher education teaching quality assessment in practical applications [25][26][27][28][29][30][31]. e parameter optimization problem of the BP neural network and the structure determination problem of the limit learning machine are not effectively solved, and the outcomes of the college teaching quality assessment are negatively impacted as a result of this [32,33].…”