Artificial Intelligence

Part of this Programme

IT Engineering

Level of Qualification|Semesters|ECTS

Bachelor | Semestral | 5

Year | Type of course unit | Language

3 |Mandatory |Português

Total of Working Hours | Duration of Contact (hours)

140 | 60

Code

ULHT260-2129

Recommended complementary curricular units

n/a

Prerequisites and co-requisites

n/a

Precedences

Não

Professional Internship

Não

Syllabus

- History of AI - Machines of Turing - Neural Networks of McCulloch and Pitts - Finite state automata - Representation of knowledge in Rational Agents - Informed Search - Stochastic Search - Classical techniques of AI in Machine learning: classification and categorization. - Basic Techniques of AI in Data Science: Deep Learning

Objectives

The learning objectives of this course include: (1) In-depth understanding of the conceptual aspects that give rise to AI, namely computation via symbol manipulation, and network-based computation of neurons; (2) Understanding and implementation of rational agents; (3) Classical search algorithms, DFS, BFS, A *; (4) Stochastic search and genetic algorithms; (5) essential bases of artificial intelligence in the domains of machine learning and data science.

Teaching methodologies and assessment

The course will be given as a set of lectures and practical sessions. In order to achieve the different objectives of this course, the teaching approach will be based on solving a small set of problems throughout the course, adding the different components of an IA solution incrementally, explaining the relevant theoretical and practical knowledge. The evaluation will consist of a series of tests, some of which may be practical implementations (eg, completing a program for it to work), along with the practical application of a basic IA system from scratch, which uses investigative techniques to specific problem.

References

Russell R & Norvig P (2010) Artificial Intelligence: A Modern Approach. Third Edition, Prentice Hall.

Nilsson, N. J. (2014). Principles of artificial intelligence. Morgan Kaufmann.

Davis, R., Shrobe, H., & Szolovits, P. (1993). What is a knowledge representation?. AI magazine, 14(1), 17.

Mitchell, M. (1998). An introduction to genetic algorithms. MIT press.