DOI: https://doi.org/10.36347/sjet.2025.v13i07.004

Pages: 487-491

With the rapid development of artificial intelligence and machine learning technology, cultivating talents with innovative ability and interdisciplinary comprehensive literacy has become an important goal of modern education. Traditional machine learning courses and teaching models can no longer meet the talent needs of the new era, especially in the combination of theory and practice, cross-disciplinary integration, and docking with industry. Therefore, this study focuses on the innovation of talent training models for machine learning courses, analyzes the advantages and limitations of the existing model, and proposes experimental teaching reform strategies based on project-driven, interdisciplinary integration, and real-world scenario applications. First, the course content should strengthen the combination of theoretical foundation and cutting-edge technology, and cultivate students' innovative thinking and multidisciplinary problem-solving ability through the design of interdisciplinary projects. Secondly, practical teaching should pay more attention to the cultivation of engineering practical ability, and improve students' hands-on ability and practical application ability through projects that connect real data sets with industry needs. Finally, the cultivation of innovative talents also needs to closely integrate classroom learning with industry needs through school-enterprise cooperation and other forms, so as to provide students with a broader practical platform. In summary, the innovative machine learning course design and experimental teaching model can effectively improve students' comprehensive quality and provide high-quality compound talents for industrial development and academic research.