Machine Learning I

Code:

CC2008

Acronym:

CC2008

Level:

200

Keywords
Classification	Keyword
OFICIAL	Computer Science

Instance: 2024/2025 - 2S

Active?	Yes
Responsible unit:	Department of Computer Science
Course/CS Responsible:	Bachelor in Artificial Intelligence and Data Science

Cycles of Study/Courses

Acronym	No. of Students	Study Plan	Curricular Years	Credits UCN	Credits ECTS	Contact hours	Total Time
L:BIOINF	25	Official Study Plan	2	-	6	48	162
L:CC	33	study plan from 2021/22	2	-	6	48	162
			3
L:IACD	78	study plan from 2021/22	2	-	6	48	162

Teaching language

Portuguese

Objectives

This course introduces Machine Learning (ML), providing students with a brief historical background and reference to some of its most relevant applications.

It is intended that students make first contact with various tasks and approaches involved in ML problems and that they can, in this way, identify the most appropriate strategies.

Learning outcomes and competences

It is intended that students:

• know the various types of machine learning (ML) tasks;


• identify problems that can be addressed as ML tasks;


• know the algorithmic fundamentals of ML;


• know the phases of an ML project;


• know the main methods/algorithms for each type of ML task and understand the essentials of its operation;


• correctly evaluate the results of an ML project;


• develop and implement strategies in ML algorithms that aim to overcome domain challenges;


• properly use software for solving simple ML problems.

Working method

Presencial

Program

• Introduction to Machine Learning (ML) 


• Supervised learning




• classification and regression problems


• evaluation metrics


• performance estimation methodologies


• linear and non-linear supervised learning algorithms (e.g. linear discriminant, linear regression, decision trees, k-NN, Naive Bayes, SVM, ANN) 




• Unsupervised learning




• similarity and distance metrics


• partitional and hierarchical clustering


• clustering validation






• frequent pattern mining


• unsupervised learning algorithms (e.g. k-Means, DBSCAN, Apriori)




• Ensemble learning




• bagging and boosting


• ensemble algorithms (e.g. Random Forest, AdaBoost) 




• Advanced topics




• imbalanced domain learning


• anomaly detection


• meta-learning




• Integration of ML in a data mining project: methodologies.

Mandatory literature

João Moreira, Andre Carvalho, Tomás Horvath; A General Introduction to Data Analytics, John Wiley & Sons, 2018. ISBN: 978-1-119-29626-3
João Gama, André Carlos Ponce de Leon Ferreira de Carvalho, Katti Faceli, Ana Carolina Lorena, and Márcia Oliveira; Extração de Conhecimento de Dados: Data Mining, Edições Sílabo, 2017. ISBN: 978-972-618-914-5

Complementary Bibliography

Mitchell, T. M.; Machine learning, McGraw Hill, 2017
Flach P.; Machine Learning, Cambridge University Press., 2012. ISBN: 978-1-107-42222-3

Teaching methods and learning activities

The expository method will be used in theoretical classes, with an organized view of the program themes being presented.

Practical classes will consist of solving exercises to apply the concepts introduced in theoretical classes.

Software

Python

Evaluation Type

Distributed evaluation with final exam

Assessment Components

designation	Weight (%)
Exame	30,00
Trabalho prático ou de projeto	40,00
Teste	30,00
Total:	100,00

Amount of time allocated to each course unit

designation	Time (hours)
Elaboração de projeto	56,00
Estudo autónomo	50,00
Frequência das aulas	56,00
Total:	162,00

Eligibility for exams

The final evaluation has a distributed component consisting of two tests and a practical assignment.

The student who does not deliver and present the practical assignment does not have frequency and thus is not eligible for the final test or supplementary exam.

Calculation formula of final grade

Final grade calculation formula:

0.3 *  T1+ 0.4 * TP + 0.3 * T2

where

T1 is the grade of the first test,

TP is the grade of the practical assignment,

T2 is the grade of the second test - to be held on the date of the final exam.

To be approved, the student must obtain a minimum grade of 35% in each of the three components.

Special assessment (TE, DA, ...)

Working students and their equivalents dismissed from classes must, at intervals to be agreed with the teachers, present the progress of their work and present these simultaneously with ordinary students.

Classification improvement

The assessment of practical work is not subject to improvement.

The student can improve the theoretical grade by taking the supplementary exam.