The laboratory intends to introduce some machine learning techniques for image processing. The discussion is strongly application-oriented. Those who want a more theoretical and more extensive treatment can attend the Big-data Analytics course or Data Mining and Classification (in Italian). Course structure. 1 - Introduction to the course 2 - Python 1 3 - Python 2 4 - Python 3 Home work on Python to submit on the course page Those who know Python can skip 2-3-4 lessons but must do home-work 5 - Machine learning 1 6 - Machine learning 2 7 - Scikit-Learn: exercises  Home work on Scikit-learn to submit on the course page 8 - Neural Networks 1 9 - Neural Networks 2 10 - Neural Networks 3 11 - Tensorflow & Keras: exercises Home work on Keras to submit on the course page 12 - Image processing with NN 13 - Retrain: exercises 14 - Exercises on image processing Final Home work to submit on the course page The exam will consist in the evaluation of the home-works carried out during the course. The teacher can ask to illustrate in detail in class the code prepared by the student. Failure to attend classes or not to deliver homeworks will prevent you from passing the exam.

• Verranno distribuiti appunti del docente, articoli, capitoli di libri, links a documentazione presente sul WEB, software code. • I materiali saranno in gran parte consultabili sul sito dei corsi on-line del dipartimento (Moodle).