AIMS AND CONTENT

LEARNING OUTCOMES

The course is aimed at providing machine learning basic and advanced techniques for data driven signal processing models to be used within autonomous systems design. In particular, perception and control modules in autonomous systems rely more and more on signal processing approaches whose parametrization can be learned from observing multimedia heterogeneous signals produced by the artificial system while performing specific tasks. The course analyses data acquisition and processing tradeoffs between edge and cloud resources on the basis of real-time, computational and energy consumption requirements. Specific attention will be devoted to high dimensional data processing on the edge (with real practical examples in Python), showing how deep learning approaches can be adapted and optimized for working with limited computational capabilities.

AIMS AND LEARNING OUTCOMES

• Learning of representations from heterogeneous raw data
• Principles of supervised learning
• Elements for different methods for deep learning: convolutional networks and recurrent networks
• Edge computing principles and limitations – computational aspects
• Theoretical knowledge of and practical experience of training networks for deep learning including optimization using stochastic gradient descent
• New progress in methods for deep learning: Generative Adversarial Networks, Variational Autoencoders, Flow-based models, Long short-term memory networks
• Analysis of models and representations for automatic decision making for autonomous systems (deep reinforcement learning)
• Learning of collaborative models for multiple autonomous systems
• Transfer learning with representations for deep learning
• Application examples of edge deep learning for real autonomous systems

TEACHING METHODS

The lessons alternate theoretical explanations with practical exercises. Theoretical explanations are frequently exemplified with the analysis, execution, and debugging of code fragments directly on the teacher's PC. All the material seen in class (slides and practical examples) is shared through the AulaWeb and Teams platforms. Students can interact directly with the teacher during lessons or through the Teams platform.

TEACHERS AND EXAM BOARD

Exam Board

SANDRO ZAPPATORE (President)

CARLO REGAZZONI

ROBERTO BRUSCHI (President Substitute)

LUCIO MARCENARO (President Substitute)

LESSONS

LESSONS START

https://corsi.unige.it/10378/p/studenti-orario

Class schedule

The timetable for this course is available here: Portale EasyAcademy

EXAMS

EXAM DESCRIPTION

Development and presentation of a practical project work.

Exam schedule