Unit MACHINE LEARNING
- Course
- Informatics
- Study-unit Code
- A002051
- Curriculum
- In all curricula
- Teacher
- Valentina Poggioni
- Teachers
-
- Valentina Poggioni
- Hours
- 68 ore - Valentina Poggioni
- CFU
- 9
- Course Regulation
- Coorte 2025
- Offered
- 2025/26
- Learning activities
- Caratterizzante
- Area
- Discipline informatiche
- Academic discipline
- INF/01
- Type of study-unit
- Obbligatorio (Required)
- Type of learning activities
- Attività formativa monodisciplinare
- Language of instruction
- INGLESE
- Contents
- MLP Neural Networks; Training methods and algorithms; CNN; RNN: LSTM and GRU; Autoencoders; Attention Models; Transformers; Discriminative and Generative Models; GAN, VAE and Diffusion Models; Representational Learning; Text embedding; Clustering; Dimensionality Reduction; Anomaly Detection; Introduction to Adversarial Machine Learning.
- Reference texts
- - Prince. Understanding Deep Learning. MIT Press. 2023 - Goodfellow, Bengio, Courville. Deep Learning. 2018. (also free online at deeplearning https://www.deeplearningbook.org/) - Nielsen, Neural Networks and Deep Learning. 2019 (online book, avalilable at http://neuralnetworksanddeeplearning.com/) - Charu C. Aggarwal, Neural Networks and Deep Learning. Springer, 2019 - Daniel Jurafsky and James H. Martin. 2025. Speech and Language Processing, 3rd edition. Online manuscript released January 12, 2025. https://web.stanford.edu/~jurafsky/slp3.
- Educational objectives
- The student will know the fundamentals and most important machine and deep 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 natural language processing 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. He/she will know the main generative approaches, the attention mechanism and the transformer architecture that is at the base of modern Large Language Models
- Prerequisites
- Suggested courses:
"Introduction to artificial intelligence" e "ARTIFICIAL INTELLIGENT SYSTEMS (1 semester)" - 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
- MLP Neural Networks; Training methods and algorithms; CNN; RNN: LSTM and GRU; Autoencoders; Attention Models; Transformers; Discriminative and Generative Models; GAN, VAE and Diffusion Models; Representational Learning; Text embedding; Clustering; Dimensionality Reduction; Anomaly Detection; Introduction to Adversarial Machine Learning.