Leveraging Deep Learning for Enhanced Computer Network Teaching: A Research and Application Study

Abstract

With the introduction of new engineering disciplines, classroom teaching methods for computer-related majors have transitioned from traditional theoretical instruction to advanced pedagogical approaches that cultivate students' cognitive development. The emphasis lies in fostering students' higher-order thinking abilities, with the core teaching philosophy centered on improving hands-on competencies. This encompasses exercises in critical and creative thinking, which serve to enhance both cognitive and non-cognitive abilities. Effectively integrating deep learning with advanced classroom methodologies and applying them to comprehensive practical courses within new engineering disciplines—such as computer network courses—can strengthen students' capacity to solve complex problems through hands-on practice. For example, incorporating artificial intelligence (AI)-related technologies into the experimental content of network security classrooms and employing various virtualization technologies to construct network simulation platforms can validate the effectiveness of technological applications. These approaches fully stimulate students' interest in learning, enabling them to engage with practical course content through immersive learning experiences. Through graded and progressive experimental stages, students can systematically enhance their hands-on abilities. Effective course practice has demonstrated that this method not only facilitates more detailed instructional control for educators but also improves student classroom participation and exercises their practical skills, thereby fully enhancing the teaching quality of comprehensive practical training courses.