基于L-M优化算法的学分绩点预测模型构建

Construction of the Prediction Model of GPA Based on L-M Optimization Algorithm

利用学生历史成绩数据和课程之间关系,构建基于BP神经网络的学分绩点预测模型,具有一定的理论和实际应用价值。BP神经网络能够自适应学分绩点统计中课程之间的层次和网络关系,非常适合用于复杂非线性关系的预测。比较了不同算法训练的网络预测结果,发现L-M优化算法预测性能最优。最后,运用函数进行仿真,然后将仿真结果与样本数据对比,验证了L-M优化算法预测模型准确性高,能够用于学分绩点的预测。

According to the relationship between student achievement data and the course,a prediction model of GPA based on BP neural network is built.BP neural network is very suitable for the prediction of complex nonlinear relation,so it can be used to adjust the level and network relationship between the courses in the grade point statistics.In comparison with the prediction results of different algorithm training network,L-M prediction optimization is of the best performance.Finally,simulation is carried out using the function,then the result is compared with the sample data,verifying the optimization algorithm of L-M prediction model with high accuracy,which can be used to predict the GPA.