OVERVIEW

The course covers the main issues related to Human-Computer Interaction. In particular, the course provides the theoretical principles, models and methodologies for the implementation of interactive systems based on computer and customized to the needs of the users. Moreover, the execution of monographic projects makes it possible to acquire operational skills for the design and implementation of interactive systems for data input/acquisitiona, learning, communication.

AIMS AND CONTENT

LEARNING OUTCOMES

Man-machine interaction. Theoretical principles, models and methodologies. Design, implementation and evaluation of interactive systems for data input/acquisition, learning, communication. 

AIMS AND LEARNING OUTCOMES

By taking the course, the student should come to possess a broad knowledge of state-of-the-art deep learning techniques (dense, convolutional, recurrent, attention-based networks). For each topic covered, the student will have the opportunity to learn the theoretical foundations, and to study some application examples. Exercises are proposed, and usually solved in class, for each topic in order to stimulate application and test knowledge acquisition. The examples and exercises in the course will use the python language and the Keras/Tensorflow library.

The project that will be agreed upon for the exam is aimed at stimulating and verifying the student's design and implementation skills, as well as the field operational verification of a significant part of the acquired knowledge.

The learning outcomes relate to the realization of the above training objectives, including through the implementation of a project. At the end of the course the student will be able to analyze and design deep learning solutions in various types of applications

TEACHING METHODS

Lectures face-to-face, with use of slides, and examples/exercises carried out on the PC (or in tele-learning, if made necessary), mainly using the Keras/Tensorflow library, in python language. Student reception. Proposal, implementation and discussion of a project.

SYLLABUS/CONTENT

Machine learning

• Multilayer perceptron
• Training deep neural networks
• Pre-training and fine tuning
• Optimizers
• Regularization
• Convolutional neural network architectures
• Object detectors
• Processing of sequences
• Recurrent neural networks
• Bi-directional neural networks
• Attention mechanisms
• Auto-encoders
• Generative adversarial networks
• Explainable machine learning

RECOMMENDED READING/BIBLIOGRAPHY

A. Geron, Hands-On Machine Learning With Scikit-Learn and Tensorflow: Concepts, Tools, and Techniques to Build Intelligent, O’ Reilly

I. Goodfellow, Y. Bengio and A. Courville, Deep Learning, The MIT Press

Lecture notes and other material suggested by the lecturer during the course

TEACHERS AND EXAM BOARD

Exam Board

FRANCESCO BELLOTTI (President)

LUCIO MARCENARO (President Substitute)

LESSONS

LESSONS START

https://easyacademy.unige.it  

Class schedule

The timetable for this course is available here: Portale EasyAcademy

EXAMS

EXAM DESCRIPTION

The exam includes a written test and the execution of a monographic project on the design and development of interactive systems for the introduction / acquisition of data, learning, or communication. Alternatively, only attending students can replace the written test with a continuous and detailed assessment during the lesons of the level of knowledge acquired.

ASSESSMENT METHODS

The exam assesses the acquisition of the concepts contained in the course, the ability to apply these concepts to the design, implementation and evaluation of an interactive system for data input/acquisition, learning, communication. The exam is not passed when the theoretical and practical training objectives have not been achieved; in this case the student is invited to deepen the study and to use further explanation by the teacher concerning the theoretical or practical contents of the course.

Exam schedule