Using a probabilistic neural network algorithm to measure the level of education quality

The traditional method of determining the quality of education is too unambiguous and unreasonable, which is not suitable for a comprehensive assessment of students' abilities. The purpose of the article is to justify the use of a probabilistic neural network algorithm. Research methods. The reliability of the presented results is ensured by the analysis of scientific literature, modeling of a probabilistic neural network, comparative analysis of models and evaluation of the effectiveness of the model. Research results. In this paper, a probabilistic neural network (PNN) algorithm is used to determine the quality of education by considering the important influence between different student achievements. The PNN algorithm comes from the Bayesian decision rule and uses the nonlinear Gauss Parsen window as a probability density function. Since the PNN model has strong nonlinear and anti-interference properties, it is suitable for determining the quality of education by classifying student achievements. In addition, this article also discusses the impact of various evaluation models on the accuracy and effectiveness of classification. In addition, the influence of the spread value on the PNN model is also discussed. Scope of application. Finally, evidence is used to determine the quality of education. Conclusions. Experimental results show that the detection accuracy can reach 95%, and the detection time is only 0.0156 s based on the proposed method. That is, the method is a very practical detection algorithm with high accuracy and efficiency. In addition, it also contains information on how to further improve the quality of teaching. It is proved that the use of the PNN model makes it possible to accurately classify the achievements of students according to the quality criterion.