IPT Logotipo do IPT

Engenharia Informática

Intelligent Systems

<< back to Curriculum Plan

Publication in the Diário da República: Despacho n.º 8644/2020 - 08/09/2020

6 ECTS; 2º Ano, 2º Semestre, 28,0 PL + 28,0 TP , Cód. 911941.

Lecturer
- Manuel Fernando Martins de Barros (1)(2)
- Ana Cristina Barata Pires Lopes (2)

(1) Docente Responsável
(2) Docente que lecciona

Prerequisites
Not applicable.

Objectives
1. Characterize Artificial Intelligence and its applicability.
2. Represent, acquire, manipulate and apply knowledge in computer systems;
3. Implement search algorithms, assessing its advantages and limitations.
4. Apply artificial intelligence techniques to game;
5. Model and solve problems with Logic Programming.
6. Characterize the different planning methods and algorithms for planning.
7. Apply the different approaches to machine learning, and evolutionary computing.

Program
1. Introduction to Artificial Intelligence (AI): Overview and brief history of AI and its applications.

2. Intelligent agents: a) rational agents. b) Nature of the environments. c) Agent structures.

3. Problem Solving Methods: a) Search methods: uninformed, informed, heuristic, A *. b) Game theory and player agents. c) Constraint satisfaction problems.

4. Knowledge Representation and Reasoning. a) Propositional Logic. b) Predicate Logic. c) Logic programming. d) Planning.

5. Machine Learning:
a) Types of Learning.
b) Inductive learning and decision trees.
c) Artificial Neural Networks: Basic principles and fundamental algorithms.
d) Support Vector Machines.
e) Reinforcement Learning.
f) Deep Learning.

6. Evolutionary computing:
a) Genetic algorithms;
b) Evolutionary strategies;
c) Genetic programming;
d) Hybrid optimization techniques.

7. a) Implementation of machine learning kits for application prototyping. b) Critical selection of assumptions. c) Suitable selection of machine learning algorithms to problems.

Evaluation Methodology
Final assessment is the average of the following components:
- Written test (test or exam)
- Labs

Final Grade = Average (Written Test, Labs)

Note:
1. In both components a minimum of 40% is required.
2. The final evaluation must be greater than or equal to 10 values (out of 20).

Bibliography
- Alpaydin, E. (2014). Introduction to Machine Learning. (Vol. 3ed.). mitpress.mit.edu: MIT Press
- Bishop , C. (2006). Pattern Recognition and Machine Learning . (Vol. 1). Springer-Verlag New York: Springer
- Russel, S. e Norvig, P. (2020). Artificial Intelligence – A Modern Approach.. (Vol. 4). http://aima.cs.berkeley.edu/: Prentice-Hall
- Simões, A. e Costa, E. (2008). Inteligência Artificial – Fundamentos e Aplicações. Segunda Edição. (Vol. 2). FCA - Editora de Informática: FCA - Editora de Informática

Teaching Method
Teaching model based on lectures of theoretical concepts and practical examples, practical laboratory classes and autonomous work. Preference will be given to the presentation, analysis of problems/approaches in the area of AI that motivate learning

Software used in class
Python Programming Language
Anaconda Framework
Jupiter Notebook
Scikit-learn
TensorFlow
Weka (https://sourceforge.net/projects/weka/)

 

 

 


<< back to Curriculum Plan
NP4552
Financiamento
KreativEu
erasmus
catedra
b-on
portugal2020
centro2020
compete2020
crusoe
fct
feder
fse
poch
portugal2030
poseur
prr
santander
republica
UE next generation
Centro 2030
Lisboa 2020
co-financiado