THREE-DIMENSIONAL MODELING

Course objectives

General objectives: The aim of the course, which is the most advanced within the Master's Degree in Artificial Intelligence and Robotics, is to provide an overview to the following research topics: learning methods in computational vision, model recognition, human-robot interaction and cognitive robotics. The topics are presented by active researchers in these fields in order to present the student with research problems and relevant and recent application themes in Artificial Intelligence and Robotics. To this end, the courses include both the presentation and discussion of scientific articles, and an advanced project work. The learning objective of the course is to provide the knowledge needed to undertake research work in these fields using practical tools for experimental validation. Specific objectives: Knowledge and understanding: The course is the most advanced in the Master for Artificial Intelligence and Robotics and offers an overview of different research topics, such as: learning methods in computational vision, pattern recognition, person-robot interaction, and automatic reasoning in robots. The topics are covered by researchers active in the field and with the aim of introducing the student to research problems and recent and relevant applications in Artificial Intelligence and Robotics. Applied knowledge and understanding: The course provides the knowledge necessary to undertake research work in these fields using practical tools for experimental validation. Critical and judgment skills: The course proposes advanced methods to study, understand and apply results reported on scientific articles, and integrate these results to create innovative Artificial Intelligence applications. The student learns how to use results from the literature as a basis for new research. Communication skills: Group activities in the classroom and the need to make presentations to the class allow the student to develop the ability to communicate and share the knowledge acquired and to compare herself with others on the topics of the course. Learning ability: In addition to the classic learning skills provided by the theoretical study of the teaching material, the course develops methods stimulate the student to deepen his knowledge of some of the topics she presents to the course and to the work group. Furthemroe the course stimulates the student to effectively apply both the concepts and the techniques learned during the course.

Channel 1
CHRISTIAN NAPOLI Lecturers' profile

Program - Frequency - Exams

Course program
The course "ELECTIVE IN ARTIFICIAL INTELLIGENCE" is structured into four main modules: Course Introduction and Presentation: This module will present the course objectives, expectations, and available resources. Students will receive an overview of the main topics that will be covered throughout the course, with an introduction to the fundamental concepts of Artificial Intelligence, Machine Learning, and Deep Learning. Preprocessing and Domain Transformation for Advanced Machine Learning: This module will explore essential data preprocessing techniques for building effective machine learning models. Topics such as normalization, standardization, handling missing data, and domain transformation techniques will be covered. Students will learn how to prepare data to enhance model performance. Advanced Machine Learning and Deep Learning: In this module, advanced Machine Learning concepts, including optimization and regularization techniques, will be explored in depth. Additionally, detailed coverage of Deep Learning architectures, such as convolutional, recurrent, and deep neural networks, will be provided, with practical applications across various domains. Geometric Deep Learning: The final module will focus on Geometric Deep Learning, an emerging field that combines geometry with machine learning. Students will explore how to use graphs and other geometric structures to build learning models that capture complex structural information. Advanced use cases and real-world applications will be discussed.
Prerequisites
Python, elements of programming, machine learning, computer vision.
Books
"Deep Learning" by Ian Goodfellow, Yoshua Bengio, and Aaron Courville - This book provides a solid foundation on Deep Learning concepts, covering both theoretical and practical aspects, and is considered a key reference in the field. "Geometric Deep Learning: Grids, Groups, Graphs, Geodesics, and Gauges" by Michael M. Bronstein, Joan Bruna, Yann LeCun, Arthur Szlam, and Pierre Vandergheynst - This book explores the intersection between geometry and Deep Learning, offering a deep insight into Geometric Deep Learning techniques. "Pattern Recognition and Machine Learning" by Christopher M. Bishop - An essential text for understanding the fundamentals of advanced Machine Learning and pattern recognition techniques, widely used as a reference for many methodologies covered in the course. Instructor-provided materials - Lecture notes, scientific papers, and additional resources will be made available to students to supplement their study and provide deeper insights into specific topics covered in the course.
Teaching mode
Lectures will be held online
Frequency
In presence, mandatory to opt for the TYPE A exam
Exam mode
Exam A) Students that have presented their project during the course: Project + report (in the form of a scientific paper) B) Students that have NOT presented their project during the course: Project + report (in the form of a scientific paper) + oral exam
Bibliography
TEXTBOOKS FOR REFERENCE Richard Szeliski Computer vision: algorithms and applications Springer Science & Business Media, 2019 Peter Corke Robotics, vision and control Springer, 2017.
Lesson mode
Lectures will be held in class
  • Academic year2025/2026
  • CourseArtificial Intelligence and Robotics
  • CurriculumSingle curriculum
  • Year2nd year
  • Semester1st semester
  • SSDING-INF/05
  • CFU6