基于一种改进BP神经网络算法的教学质量评价研究

Teaching Quality Evaluation Based on an Improved BP Neural Network Algorithm

在教学管理问题的研究中,针对教学质量评价的非线性特征以及教学质量评估体系中存在的诸多非定量的因素,建立教学质量评价的BP神经网络模型。评价模型对已有评价体系中的主观性因素进行量化,并利用神经网络的自学习,自适应及非线性逼近能力进行量化评价的计算。对模型中用到的BP算法和代数算法分别进行了理论上的分析和训练结果的对比,为教学质量评价模型提供了可行的解决方案。

Considering the nonlinear characteristics of teaching quality and the existence of many non - quantitative factors in the evaluation system, a BP neural network model of teaching quality evaluation has been built in this paper. The model can quantify the subjectivity factor in the existing evaluation system. By utilizing the properties of self-study and self-adaptation of neural network that can approximate any nonlinear continuous function, the model has calculated quantified evaluation. BP algorithm and algebraic algorithms used in the model were carried out theoretical analysis and comparison of the results of the training, which can provides a feasible solution for the teaching quality evaluation model.