OVERVIEW

The course aims at introducing the learner to the theory and applications of machine learning.

AIMS AND CONTENT

LEARNING OUTCOMES

The course aims at introducing the learner to fundamental state of the art knowledge and tools on machine learning algorithms/models. The goal is for students to become able to tackle real-world problems, using supervised and unsupervised learning techniques.

AIMS AND LEARNING OUTCOMES

The main objective of the course is for the student to come to possess a broad knowledge of state-of-the-art deep learning techniques (dense, convolutional, recurrent networks). For each topic covered, the student will have the opportunity to learn the theoretical foundations, and to study some application examples. 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 sk-learn and Keras/Tensorflow libraries.

The learning outcomes relate to the realization of the above learning objectives, including through the analysis of application cases.

PREREQUISITES

Fundamentals of programming (particularly python).

TEACHING METHODS

Lectures face-to-face, using slides, and examples/exercises carried out on the PC, mainly using the sk-learn and Keras/Tensorflow libraries, in python language. Student Reception. Proposal, implementation and discussion of a project.

SYLLABUS/CONTENT

Machine learning

• Introduction to machine learning
• Pre-processing
• Metrics for regression and classification
• Linear regression
• Gradient descent
• Classification
• Training
• Regularization
• Decision trees
• Ensamble learning
• Random forests
• Neural networks. Multilayer perceptron for regression and classification
• Principal Component Analysis
• Unsupervised machine learning (clustering)
• (Genetic algorithms)

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)

MATTEO FRESTA

RICCARDO BERTA (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 student will propose and preliminairly agree with the teacher(s) a dataset onto which to prepare a Jupyter notebook (similar to those seen at lecture) for critically implementing a ML task (e.g., classfication, regression, clustering). This also includes: pre-processing, training of various models, hyperparameter tuning, overall testing.

During the exam the student will present this work. Then, the teachers will ask questions potentially on all the topics of the course. 

ASSESSMENT METHODS

Verification of the knowledge acquired and the ability to apply it in contexts other than those presented in class will be assessed through questions in the interview or written examination.

The evaluation will also take into account the student's participation during the course.

Exam schedule