Research on Course Teaching Quality Evaluation Based on Improved BP Neural Network Algorithm

Abstract

BP neural network is a model that abstractly portrays the neuronal system of the brain, however, the selection of the number of neurons in the Hide layer becomes the key to the construction of the neural network model. This paper addresses the problems of Hide layer selection in the transmission model, improves the "in-and-out method" and applies it to the neural network model, and combines the improved nonlinear Levenberg-Marquardt function to make the evaluation model operation process faster and more reasonable. Then the evaluation model was applied to the SPOC+MOOC learning evaluation of a major course at University L to assess student learning behavior. The results show that the course teaching quality evaluation model based on improved BP neural network algorithm has fast convergence speed and small error, and its evaluation results can effectively reflect the level of course teaching quality, and the analysis results have certain reference, which can provide reference basis for improving and improving online course teaching.