Advanced Topics on Artificial Intelligence

Code:

CC4022

Acronym:

CC4022

Level:

400

Keywords
Classification	Keyword
OFICIAL	Computer Science

Instance: 2022/2023 - 1S

Active?	Yes
Responsible unit:	Department of Computer Science
Course/CS Responsible:	Master in Computer Science

Cycles of Study/Courses

Acronym	No. of Students	Study Plan	Curricular Years	Credits UCN	Credits ECTS	Contact hours	Total Time
E:BBC	0	PE_Bioinformatics and Computational Biology	1	-	6	42	162
M:BBC	5	The study plan since 2018	1	-	6	42	162
M:CC	13	Study plan since 2014/2015	1	-	6	42	162
M:DS	16	Official Study Plan since 2018_M:DS	1	-	6	42	162
			2

Teaching language

Portuguese and english
Obs.: Classes will be taught in English if there are students that are not Portuguese native speakers.

Objectives

Provide students with knowledge about new AI developments that involve advances in areas as diverse as logic, statistics and operations research.

Emphasis will be placed on:
- directed and non-directed probabilistic graphical models, including inference and learning of parameters and structure; connection to linear classifiers and neural networks
- logical representation: First order logic (FOL) and Datalog for structure representation; learning logical programs in Inductive Logic Programming (ILP).
- integration: Statistical relational learning (SRL) and neural-logical networks.

The course requires skills acquired in Design and Analysis of Algorithms, Artificial Intelligence and Data Mining.

Learning outcomes and competences

Students will develop competences on the usage of artificial intelligence and search / optimization methods in practical situations, in which a part of the knowledge is available in data sets or databases.

Working method

Presencial

Pre-requirements (prior knowledge) and co-requirements (common knowledge)

Algorithm Design and Analysis, Artificial Intelligence, Data Mining I

Program

1. Review of the main concepts in artificial intelligence
2. (Probabilistic) Graphical Models
3. Knowledge-based decisions systems
4. Algorithms for search and optimization
5. Learning

Mandatory literature

Daphne Koller; Probabilistic graphical models. ISBN: 978-0-262-01319-2
Kevin P. Murphy; Machine learning. ISBN: 978-0-262-01802-9
Battiti Roberto; The LION way. ISBN: 9781496034021
Stuart Jonathan Russell; Artificial intelligence. ISBN: 978-1-292-40113-3

Complementary Bibliography

Russell Stuart J. (Stuart Jonathan); Artificial intelligence. ISBN: 9780132071482 pbk
Hastie Trevor; The elements of statistical learning. ISBN: 9780387848570
Haykin Simon S. 1931; Neural networks. ISBN: 9780132733502

Comments from the literature

There are two reommendations for Russel's book. Although they contain repeated material, the 4th edition contains more details about deep neural networks. Some material of the 3rd edition was not included in the 4th edition.

Online:

• Machine learning: An Introduction to Statistical Learning. https://www.statlearning.com

• Reinforcement Learning: An Introduction. Richard S. Sutton and Andrew G. Barto.

• http://webdocs.cs.ualberta.ca/~sutton/book/ebook/

• http://people.inf.elte.hu/lorincz/Files/RL_2006/SuttonBook.pdf

Teaching methods and learning activities

* Lectures: presentation of the program topics and discussion of examples.
* Project: two homeworks to be developed by the students, iin groups of at most 3
  The lecturers will propose a number of challenges, but the students may choose a task, 
Evaluation: a report, code, and a presentation.

keywords

Physical sciences > Mathematics > Applied mathematics > Operations research
Physical sciences > Mathematics > Algorithms
Physical sciences > Computer science > Cybernetics > Artificial intelligence

Evaluation Type

Distributed evaluation with final exam

Assessment Components

designation	Weight (%)
Exame	50,00
Trabalho escrito	20,00
Apresentação/discussão de um trabalho científico	30,00
Total:	100,00

Amount of time allocated to each course unit

designation	Time (hours)
Elaboração de relatório/dissertação/tese	40,00
Estudo autónomo	80,00
Frequência das aulas	42,00
Total:	162,00

Eligibility for exams

* Submitting the requested assignments, and obtaining a grade of 50% or more.

Calculation formula of final grade

* Tests and exam have a minimum grade, at least 30%

0.50 * grade at exam + 0.50 * grade at assignments

If the student has a positive grade with the tests and assignments (and minimum grade in the tests) he/she will be excused from taking the exam. In this case, the student can take the exam as an improvement.

Students who are unable or unwilling to take one or both tests, can go to the exam to complete the missing component.

The exam will be in the "normal" season and divided into two parts, one corresponding to the subject of the first test and the other corresponding to the subject of the second test.

Classification improvement

Final examination