Research on Teaching Quality Evaluation Model of Higher Education Teachers Based on BP Neural Network and Random Matrix

Improving teaching quality is the first task of higher education, and evaluating teaching quality is an effective measure to improve teaching quality. Combining the advantages of BP neural network and random matrix algorithm, the teaching quality evaluation model of higher education teachers is established. In this paper, the improved BP neural network and the random matrix structure are used to normalize the indicators, evaluate the teaching indicators, and build the teacher teaching quality evaluation system model. Through experimental design, the training data set is input into the model for training. In the training process, the increase and decrease ratio of learning rate, momentum term, and other parameters are adjusted to improve the prediction accuracy and convergence speed of the model. Iteration times, training time, MSE, and prediction accuracy were taken as performance comparison indexes of the model. Experiments show that the model solves the shortcomings of the existing teaching quality evaluation methods and models to a certain extent, and improves the accuracy of evaluation prediction. When the number of iterations is 133, the prediction accuracy is as high as 94.9%, which verifies the effectiveness of the model in the evaluation of teaching quality in colleges and universities. Finally, the evaluation index system of teacher teaching quality is comprehensively analyzed, and the results prove that the evaluation model of teacher teaching quality of A university is suitable for the situation of the school, can highlight the guidance, and is scientific and measurable of evaluation.