Machine Learning and AI in Manufacturing Analytics 2.5 credits

**Transform manufacturing performance with the power of AI and machine learning.**
*Machine Learning and AI in Manufacturing Analytics* equips professionals with the tools and knowledge to harness predictive modeling, anomaly detection, and explainable AI to improve quality, reduce waste, and optimize industrial processes. Through hands-on experience with real manufacturing data, participants gain practical expertise in modern machine learning techniques, robust validation methods, and responsible AI practices including transparency, fairness, and risk management. This course emphasizes the deployment of interpretable, sustainable, and trustworthy AI solutions that enhance decision-making and support the transition toward more efficient, resilient, and data-driven manufacturing system.

This course introduces machine learning and artificial intelligence methods for manufacturing analytics, focusing on how data-driven models can support process optimization, quality monitoring, defect detection, and operational decision-making. Emphasis is placed on practical industrial applications, responsible AI, and sustainability-oriented manufacturing improvements. The course addresses how AI can contribute to energy efficiency, reduced material waste, and more robust production systems through early detection of process deviations and interpretable predictive models. Participants gain hands-on experience with industrial datasets and learn how to evaluate, deploy, and critically assess AI solutions in manufacturing environments. The course includes the following elements: - Overview of machine learning and AI for manufacturing applications - Industrial data pipelines: data collection, preprocessing, management, and governance - Supervised and unsupervised learning for process modeling and quality analytics - Introduction to deep learning for manufacturing data - Model validation, performance metrics, and uncertainty assessment - Explainable AI methods in industrial contexts (e.g., SHAP, LIME), and Responsible AI (ethics, transparency, bias, and risk management) - Use of modern large language models for manufacturing analytics support - Sustainability aspects: energy efficiency, material savings, and data-driven decision support