Introduction to Machine Learning

<p>Practical project, written report, and oral presentation</p>

<p>Verification will take place both during class and through moments of teacher-led interaction and evaluation of the assigned project and its presentation.</p>

The course is intended for students in their second or third year of master's degree, in science disciplines. The course includes an open lab to support students in the execution of projects (Integrative Teaching, 12 hours).

1) Introduction: the Knowledge Discovery process. 

• KDD process: all the steps at a glance. 
• Data understanding and data exploration. 
• Exercises: hands-on practice on simple case studies using Python libraries
• Introduction to NumPy, Pandas and Seaborn (extra support in lab)

2) Unsupervised learning methods: : methods and hands-on exercises 

• Pattern Mining and Association Rules: basic concepts and a-priori algorithm 
• Tutorials: practical exercises on simple case studies using Python libraries

3) Supervised learning: methods and practical exercises

• Classification: introduction, performance evaluation. A first simple classifier:Decision tree
• Exercises: hands-on practice on simple case studies using Python libraries
• Overview of advanced methods: Random Forest, Support Vector Machine
• Introduction to Neural Networks, project description and assignment
• Exercises: hands-on practice on advanced classification methods and Neural Networks withPyTorch (2h)

4) Introduction to Deep Learning architectures: methods and hands-on exercises

• Convolutional Neural Networks, theory and practice with PyTorch
• Recurrent Neural Networks
• Adversarial Generative Networks
• Transformers
• Graph Neural Networks

5) Design principles and reliability issues in AI-based systems

1)    “Introduction to Data Mining”, 2nd Edition by Tan, Steinbach, Karpatne, Kumar

2)    Ian Goodfellow, Yoshua Bengio, Aaron Courville, Deep Learning. MIT Press, 2016. https://www.deeplearningbook.org/

1)    Python a Machine Learning, Bellini & Guidi Mc Graw Hill

2)    Intelligent Data Analysis: An Introduction, Berthold &Hand, Springe