工科本科生毕业设计(论文)综合成绩的评定方法

Evaluation method of comprehensive performance for undergraduate in the graduation design(thesis)

该文就现行工科院校本科毕业设计(论文)现状,选用10个评价指标,由学生综合成绩等级与对应的评价指标关系提炼出5个等级理想评价指标,结合离散Hopfield神经网络的联想记忆能力,建立基于离散Hopfield神经网络的本科毕业设计(论文)综合成绩评定模型;将待评定的学生等级评价指标编码作为模型的输入,利用外积法对网络连接权值进行迭代学习,仿真结果显示,该模型能够快速、准确、直观地评定学生毕业设计(论文)环节的综合成绩。

In this paper, according to the more important ten evaluation indicators, the five grades ideal evaluation is established corresponding to the level of comprehensive performance of twenty undergraduates. Combined with associative memory capacity of discrete Hopfield neural networks, a new evaluation method of comprehensive performance for undergraduate in the graduation design （thesis） is presented. In order to evaluate the effectiveness of the assessment model, five undergraduates are assessed by the model, the network connection weights is obtained by iterative learning using the outer product method. The simulation results show that the comprehensive performance assessment model of undergraduates based on discrete Hopfield neural networks can assess the comprehensive performance of undergraduates fast, accurately and intuitively.