基于小班级并行教学的教与学优化算法研究

Teaching and Learning Optimization Algorithm for Parallel Teaching in Small Class

针对教与学优化算法后期收敛速度慢,易陷入局部最优的缺陷,提出了一种小班级并行教学的教与学优化算法。该算法将学生分成两个班级,一个班级在教学阶段之前加入学生预习阶段,以提高算法的开发能力。另一个班级引入Metropolis准则,提高算法搜索能力。选择两个班级中成绩较好的学生组成一个临时班级,并选出其中优秀学生按一定比例替换两个小班级中成绩较差学生继续寻优。每次迭代后,临时班级中的学生根据成绩好坏更新一次,直到满足条件跳出循环。在测试函数上进行仿真实验,验证了该算法的有效性。

Aimed at the problem that the teaching and learning optimization algorithm is slow and easy to fall into the local opti real, a teaching and learning optimization algorithm for parallel teaching in small class is proposed. According to the algorithm, the students are divided into two classes, and one class participates in the student preview phase before the teaching phase to improve the development capability of the algorithm. In the other class, the Metropolis criterion is introduced to improve the search capability of the algorithm. Students with better grades from these two classes are chosen to form a temporary class, from which outstanding students are chosen to replace students with poor performance in certain proportion to continue the opti mization. After each iteration, the students in the temporary class are updated once according to the grades until they fufill the condition and jump out of the loop. The effectiveness of the algorithm is verified by simulation test on the test function.