This exam is present in more than one Optional Group. Choose a group

Objectives

General goals:
The course introduces motivations, paradigms and applications of machine learning. It is to be considered an introductory course.

Specific goals:
Supervised learning: decision trees, instance-based learning, naïve Bayes, support vector machine, neural networks, deep learning, ensamble methods. Unsupervised learning: clustering, association rules. Semi-supervised learning. Reinforcement learning. Genetic algorithms and genetic programming. Issues in machine learning: underfitting, overfitting, model selection, error analysis.

Knowledge and understanding:
Students will learn which algorithms best fit which categories of problems, how to describe the application domain, how to tune parameters and hyperparameters of the model, how to test performances.

Applying knowledge and understanding:
Students will experiment the main algorithms using the Weka ML software Weka, Tensor Flow or scikit-learn.

Critical and judgmental skills:
Students will be able to will understand the categories of problems that can be efficiently solved with machine learning algorithms, under which conditions.

Communication skills:
These will be tested during written exams and project reporting.

Ability of learning:
Students will receive a solid basis for further deepening of more advanced methods, such as deep learning, probabilistic learning, and others

Channels

NESSUNA CANALIZZAZIONE

PAOLA VELARDI PAOLA VELARDI   Teacher profile

Programme

Topics Supervised learning: decision trees, instance-based learning, naïve Bayes, support vector machine, neural networks, deep learning, ensamble methods. Unsupervised learning: clustering, association rules. Semi-supervised learning. Reinforcement learning. Genetic algorithms and genetic programming. Issues in machine learning: underfitting, overfitting, model selection, error analysis.

Adopted texts

see http://twiki.di.uniroma1.it/twiki/view/ApprAuto

Bibliography

http://twiki.di.uniroma1.it/twiki/view/ApprAuto

Prerequisites

Basic notions of logic and algorithms - python and/or java

Study modes

Lessons and lab in class

Exam modes

Mid-term, final written test, project

Exam reservation date start Exam reservation date end Exam date
01/01/2020 28/01/2020 29/01/2020
19/04/2020 29/04/2020 30/04/2020
20/05/2020 14/06/2020 15/06/2020
28/07/2020 28/07/2020 29/07/2020
15/08/2020 10/09/2020 11/09/2020
Course sheet
  • Academic year: 2019/2020
  • Curriculum: Multimedia Computing and Interaction
  • Year: First year
  • Semester: First semester
  • SSD: INF/01
  • CFU: 6
Activities
  • Attività formative caratterizzanti
  • Ambito disciplinare: Discipline Informatiche
  • Exercise (Hours): 36
  • Lecture (Hours): 24
  • CFU: 6.00
  • SSD: INF/01