Advanced Topics on Artificial Intelligence

Code:

CC4022

Acronym:

CC4022

Level:

400

Keywords
Classification	Keyword
OFICIAL	Computer Science

Instance: 2017/2018 - 2S

Active?	Yes
Web Page:	http://www.dcc.fc.up.pt/~jpp/taia
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	5	PE_Bioinformatics and Computational Biology	1	-	6	42	162
M:CC	17	Study plan since 2014/2015	1	-	6	42	162
MI:ERS	8	Plano Oficial desde ano letivo 2014	4	-	6	42	162

Teaching language

English

Objectives

This course is centered on the synergies in the association of machine learning / deep learning and search / optimization methods. Based on the latest developments on search, deep learning, and reinforcement learning; these methods are considered to provide computers with quasi-human-level performance. The aim is to allow useful available information to be efficiently extracted from massive data sets (machine learning) and turned into actionable decisions (operations). Applications range from computer vision and speech recognition to high-level decision support systems, including human health, transportation and logistics, commerce and information services, and energy networks.

The course will deepen competences acquired in "Algorithm Design and Analysis" and in "Artificial Intelligence".

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.

Working method

Presencial

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

Algorithm Design and Analysis, Artificial Intelligence

Program

1. Review of the main concepts in artificial intelligence
2. Unsupervised learning
3. Knowledge-based decisions systems
4. Algorithms for search and optimization
5. Learning and Monte Carlo methods
6. Neural networks and deep learning
7. Algorithms for search, learning and optimization

Mandatory literature

Battiti Roberto; The LION way. ISBN: 9781496034021

Complementary Bibliography

Hastie Trevor; The elements of statistical learning. ISBN: 9780387848570
Wolsey Laurence A.; Integer programming. ISBN: 9780471283669
Haykin Simon S. 1931; Neural networks. ISBN: 9780132733502
Russell Stuart J. (Stuart Jonathan); Artificial intelligence. ISBN: 9780132071482 pbk

Comments from the literature

• Machine learning: An Introduction to Statistical Learning. http://www-bcf.usc.edu/~gareth/ISL/


• 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: for a concrete problem study appropriate, ad hoc techniques for tackling it.

keywords

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

Evaluation Type

Distributed evaluation with final exam

Assessment Components

designation	Weight (%)
Exame	50,00
Trabalho escrito	50,00
Total:	100,00

Amount of time allocated to each course unit

designation	Time (hours)
Elaboração de relatório/dissertação/tese	25,00
Estudo autónomo	40,00
Frequência das aulas	40,00
Total:	105,00

Eligibility for exams

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

Calculation formula of final grade

0.50 * grade at exam + 0.50 * grade at assignments

Classification improvement

Final examination

Observations

Very good grade at the assignments are eligible for exemption from the examination.