本科“机器学习”课程教学改革初探

数学知识跨度大、实际应用范围广、技术更新迭代快是“机器学习”区别于其他课程的最大特征，传统“机器学习”课程教学中数学复习与模型讲解分离、教学内容枯燥缺乏实际联系、考核内容落后于技术发展，导致本科生对机器学习模型理解困难、学习兴趣不强、自主学习意识缺乏，难以运用机器学习前沿技术解决实际问题。围绕教学方法、内容和考核3个方面，提出了“机器学习”课程教学改革措施，融合线上学习和线下推演的教学方法，增加师生互动、串联关键知识点；引入科学家故事和兴趣挑战的教学内容，丰富课堂内容、培养学习兴趣；增加基于前沿技术的实战考核，引导自主学习、探索前沿技术，成功应用于广州大学方滨兴院士本科预备班“机器学习与数据挖掘”教学实践，改善了课程的教学效果。

Preliminary study on the reform of machine learning teaching

The machine learning is different from other courses for its large span of mathematical knowledge, widely application of techniques, and fast updating of models.In traditional machine learning classes, due to the separation between review of mathematical knowledge and model explanation, boring content divorced from the reality, and the obsolete content of exam, undergraduates have difficulty in understanding machine learning models.Then they lack interest in learning and also consciousness of autonomous learning, which makes them difficult to solve practical problems with advanced machine learning technologies.Considering these facts, the teaching reform measures of machine learning course were proposed, in terms of teaching methods, content and exam.The teaching methods combined online learning and offline deduction to increase teacher-student interaction and connect key knowledge points.The teaching content introduced scientific stories and interesting challenges, which enriched the content and cultivates learning interest.The advanced machine learning technique-based practice exam was applied to enhance the capability of independent learning and explore advanced technologies.Consequently, the reform measures have been successfully applied in the machine learning teaching practice of Academician Binxing Fang undergraduate preparatory class of Guangzhou University, improving the teaching performance of machine learning course.