Course description
The AI Models course is a theoretical preparatory course for the practical application of Machine Learning and Deep Learning, designed for professionals with a STEM background who wish to acquire a solid understanding of the models underlying Artificial Intelligence. The course provides a structured overview of the main elements that make up an AI system, starting from the role of data and features, through to classic Machine Learning models, Deep Learning, and the most recent Generative AI approaches. For each family of models, the operating principles, conceptual differences, main application areas, and the most relevant use cases in industrial contexts are illustrated. Particular attention is paid to model selection criteria, performance evaluation metrics, and the trade-offs between complexity, accuracy, and data availability, providing participants with the conceptual tools necessary to understand why one model is more suitable than another in a specific application scenario. The course requires basic prior knowledge of Artificial Intelligence and is aimed at those with a basic familiarity with programming or technical and engineering concepts. At the end of the course, participants will have the essential theoretical foundations to approach advanced practical courses on the use and implementation of Machine Learning and Deep Learning models in a conscious and effective manner.
Main Topics
- Data and features for AI
- Technical focus on classic Machine Learning algorithms and description of use cases
- Technical focus on Deep Learning, definition of Neural Networks, and examples of specific algorithms
- How to choose the right model: evaluation criteria and metrics
- Introduction to Generative AI and an overview of the tools available today
Participant profile
The course is recommended for professionals with technical skills (e.g., IT specialists, engineers, data analysts) who wish to learn the theoretical concepts for potential development or practical use of AI-based solutions.
Objectives
The course aims to provide participants with a clear and structured understanding of the fundamental concepts related to Artificial Intelligence models, with particular reference to Machine Learning, Deep Learning, and Generative AI.
In particular, the course aims to:
• Understand the role of data and features in the development of AI systems
• Gain knowledge of the main families of classic Machine Learning algorithms and their respective use cases
• Understand the operating principles of neural networks and Deep Learning models
• Acquire criteria and metrics to evaluate model performance and compare alternative solutions
• Understand when and why to adopt Generative AI models and which tools are available today
• Evaluate benefits, limitations, and critical issues in adopting AI-based solutions in industrial contexts
The course represents a fundamental transition between an introductory vision of Artificial Intelligence and subsequent practical courses, providing the theoretical foundations necessary to consciously approach the design, selection, and use of AI models.
Learning outcomes
At the end of the course, participants will be able to:
• Distinguish between the main fields of Artificial Intelligence (Machine Learning, Deep Learning, and Generative AI) and understand their primary application areas in industrial contexts
• Recognize the main families of Machine Learning and Deep Learning algorithms best suited to a specific application scenario, understanding their operation at a conceptual level
• Understand the role of data, features, and evaluation metrics in the design and selection of an AI model
• Use basic technical language to communicate effectively with data scientists, developers, and other AI professionals
Participation conditions
Prior knowledge of Artificial Intelligence is required; you can start with the AI Basic course.
