This course consists of blocks of lectures and projects on the topics of machine learning concepts and algorithms, and their application to the field of autonomous mobile systems and the associate computed vision tasks.Instructor: Prof. Marco Levorato, University of California Irvine (UCI), US Instructor: Prof. Marco Levorato, University of California Irvine (UCI), US Marco Levorato is Full Professor at University of California Irvine. He joined the Computer Science department at UCIrvine in August 2013. Between 2010 and 2012, He was a post-doctoral researcher with a joint affiliation at Stanford and the University of Southern California working with prof. Andrea Goldsmith and prof. Urbashi Mitra. From January to August 2013, he was an Access post-doctoral affiliate at the Access center, Royal Institute of Technology, Stockholm. He is a member of the ACM, IEEE and IEEE Comsoc society. His research interests are focused on next-generation wireless networks, signal processing, cyber-physical systems, smart city and smart energy systems. He has co-authored over 75 technical articles on these topics, including the paper that has received the best paper award at IEEE GLOBECOM (2012). He completed the PhD in Electrical Engineering at the University of Padova, Italy, in 2009. He obtained the B.S. and M.S. in Electrical Engineering summa cum laude at the University of Ferrara, Italy in 2005 and 2003, respectively. In 2016, he received the UC Hellman Foundation Award for his research on Smart City IoT infrastructures.

-

In its first part, the course will cover basic machine learning concepts and algorithms including fundamental deep neural network architectures. Then, the course will detail and discuss perception pipelines for autonomous vehicles and the associated computer vision tasks and neural models. Then, the course will illustrate challenges in deploying these models on mobile devices and vehicles, and advanced techniques to address this issue. The sections of the course on the fundamentals of machine learning are based on the book "Deep Learning", by Ian Goodfellow, Yoshua Bengio and Aaron Courville (available online). Syllabus: Class 1: Machine learning basics. Feed forward neural networks Class 2: Convolutional neural networks. Recurrent neural networks and representation Lab: Introduction to machine learning tools - e.g., PyTorch - (2h), advanced neural models (2h) Class 3: Perception pipelines for vehicular autonomy Class 4: Adaptive models and edge computing

On site

Oral presentation

P.D.2-2 - June

Schedule: - Class 1: June 17, 9:30-12:30 (3h) - Lecture in Clarke Meeting Room* - Class 2: June 19, 9:30-12:30 (3h) - Lecture in Clarke Meeting Room* - Lab: June 20, 9:30-13:30 (4h) - Shannon Meeting Room** - Class 3June 25, 9:30-12:30 (3h) - Lecture in Clarke Meeting Room* - Class 4: June 28, 9:30-12:30 (3h) - Lecture and presentations in Clarke Meeting Room* * Clarke meeting room (DET, Cittadella Politecnica, entrance from Corso Castelfidardo 42/A, 1st floor) ** Shannon Meeting Room (DET, Sede storica, next to Classroom 12)