OVERVIEW

The course aims to deepen into the aspects of Inductive and Deductive Artificial Intelligence.
It covers both theoretical aspects and implementation-related aspects related to the use of advanced planning and machine learning techniques.

AIMS AND CONTENT

LEARNING OUTCOMES

The course aims at providing to the students knowledge of advanced inductive and deduction artificial intelligence both from a theoretical and practical perspective.

AIMS AND LEARNING OUTCOMES

The course aims at providing to the students knowledge of advanced inductive and deduction artificial intelligence both from a theoretical and practical perspective.

During the course the following skills will be developed
- personal competence
- social competence
- ability to learn to learn
- competence in project creation
- competence in project management

PREREQUISITES

- ARTIFICIAL INTELLIGENCE (cod. 111103)
- MACHINE LEARNING AND DATA ANALYSIS (cod. 86798)

TEACHING METHODS

- Frontal lesson (approx. 50% to develop ability to learn to learn)
- Laboratories (approx. 50% to develop personal competence)
- Possibility of a final project in pairs (to develop social competence, competence in project creation, and competence in project management)

For working students and students with certification of Specific Learning Disabilities (SLD), disabilities, or other special educational needs are advised to contact the instructor at the beginning of the course to arrange teaching and examination methods that, while respecting the teaching objectives, take into account individual learning styles.

SYLLABUS/CONTENT

The last 3 credits of the course ARTIFICIAL INTELLIGENCE FOR ROBOTICS I (104734):
- Automated planning with uncertainty
- Reinforcement learning in discrete domains
- Reinforcement learning in continuous domains
The last 3 credits of the course MACHINE LEARNING AND DATA ANALYSIS (cod. 86798):
- Deep neural networks (Convolutional, Attention, Memory)
- Generative models

RECOMMENDED READING/BIBLIOGRAPHY

[1] Sutton, R. S., and Andrew G. B. Reinforcement learning: An introduction. MIT press, 2018.
[2] Goodfellow, I. and Bengio, Y. and Courville, A. Deep learning. MIT press, 2016.
[3] Aggarwal, C. C. Neural networks and deep learning. Springer, 2018.

TEACHERS AND EXAM BOARD

Exam Board

DAVIDE ANGUITA (President)

LUCA ONETO (President)

ENRICO GIUNCHIGLIA (President Substitute)

ARMANDO TACCHELLA (President Substitute)

LESSONS

LESSONS START

https://easyacademy.unige.it/portalestudenti/index.php?view=easycourse&_lang=it&include=corso

Class schedule

The timetable for this course is available here: Portale EasyAcademy

EXAMS

EXAM DESCRIPTION

Oral by appointment.

ASSESSMENT METHODS

The student will solve a real problem at will by applying the techniques learned during the course.

Exam schedule