Study-unit MACHINE LEARNING
Course name | Informatics |
---|---|
Study-unit Code | A002051 |
Curriculum | Comune a tutti i curricula |
Lecturer | Valentina Poggioni |
Lecturers |
|
Hours |
|
CFU | 9 |
Course Regulation | Coorte 2022 |
Supplied | 2022/23 |
Supplied other course regulation | |
Learning activities | Caratterizzante |
Area | Discipline informatiche |
Sector | INF/01 |
Type of study-unit | Obbligatorio (Required) |
Type of learning activities | Attività formativa monodisciplinare |
Language of instruction | INGLESE |
Contents | Introduction to machine learning. Supervised semi-supervised and unsupervised approaches. Classification, clustering, anomaly detection. Application to computer vision and speech recognition. Introduction to deep learning. Advanced neural network models. |
Reference texts | Tan, Steinbach, Karpatne, Kumar. Introduction to Data Mining, 2nd Edition 2019. Pearson Charu C. Aggarwal. Neural Networks and Deep Learning: a text book. Springer 2018 |
Educational objectives | The student will know the fundamentals and most important machine learning methods based on the supervised, semi-supervised and unsupervised approach. He/she will know also some of the most known methods of deep learning , with a particular focus on computer vision and speech recognition application. He/she will able to design, implement, train and test intelligent systems for data classification, clustering and anomaly detection based on advanced neural network models. |
Prerequisites | None |
Teaching methods | In-class lessons and hands-on in computer lab |
Other information | For any other information www.unistudium.unipg.it |
Learning verification modality | Oral exam and final project. Intermediate exams during the course |
Extended program | Introduction to machine learning. Supervised, semi-supervised and unsupervised approaches. Data classification (decision trees, rule-based approach, naive bayes, nearest neighbors, SVM, neural networks, ensemble) , clustering (k-means, hierarchical approaches, density based approaches), anomaly detection. Applications to computer vision and speech recognition. Introduction to deep learning. Advanced neural networks models (convolutional NN, recurrent NN, generative models). |