-
University of Beira Interior
ARTIFICIAL INTELLIGENCE
20/07/2023: The marks for the "especial" Exam are available. Students are allowed to see their tests at office 3.22, on Friday, 21/07, 14:00 - 15:00.
07/02/2023: The marks for the "recurso" Exam are available. Students are allowed to see their tests at office 3.22, on Wednesday, 09/02, 14:00 - 15:00.
24/01/2023: The marks for the "Normal" Exam are available. Students are allowed to see their tests at office 3.22, on Wednesday, 25/01, 16:00 - 17:00.
11/01/2023: The marks for the "Teaching/Learning" (Ensino/Aprendizagem) period are available. Students are allowed to see their own tests at office 3.22, on Thursday, 12/01, 15:30 - 17:00.
1. Artificial Intelligence - Introduction
1.1 Definitions
1.2 Foundations / History
1.3 Ethical Issues: Risks and Benefits
2. Intelligent Agents
2.1 Internal Structure
2.2 Environments
2.3 States
3. Problem Solving - Search
3.1 Search Algorithms
3.2 Uninformed Search
3.3 Informed Search (Heuristic-based)
3.4 Search in Complex Environments
3.4.1 Local Search and Optimisation
3.4.2 Search in Partially Observable Environments
4. Problem Solving - Adversarial Search
4.1 Game Theory
4.2 Alpha-Beta Tree Search
4.3 Monte Carlo Tree Search
5. Problem Solving - Constraint Satisfaction Problems (CSPs)
5.1 Definition
5.2 Constraint Propagation in CSPs
5.3 Backtracking Search for CSPs
5.4 Local Search in CSPs
6. Knowledge Representation and Planning
6.1 Logical Agents
6.2 First Order Logic (FOL)
6.3 Inference in FOL
7. Learning
7.1 Taxonomy
7.2 Decision Trees, Linear Regression and Classification
7.3 Model Selection and Optimisation
7.4 Nonparametric Models
7.5 Ensemble Learning
7.6 Probabilistic Models
8. Neural Networks and Deep Learning
8.1 Feed Forward Nets
8.2 Convolutional Networks
8.3 Learning Algorithms
8.4 Recurrent Neural Networks
8.5 Transfer Learning and Cross-Domain Learning
9. Reinforcement Learning
9.1 Rewards
9.2 Passive Reinforcement Learning
9.3 Active Reinforcement Learning
9.4 Q-Learning and Deep Q-Learning
- Stuart Russell and Peter Norvig. Artificial Intelligence: A Modern Approach. Global Edition, ISBN-13: 978-1292401133, 2022.
- Denis Rothman. Artificial Intelligence by Example. Expert Insight ISBN-13: 978-1839211539, 2020.
- Michael Woolridge. A Brief History of Artificial Intelligence, Flatiron Books, ISBN-13: 978-1250770738, 2021.
- Assiduity (A) To get approved at this course, students should attend to - at least - 80% of the theoretical and practical classes
- Practical Projects (P) The practical projects of this course weights 30% (6/20) of the final mark
- (P1) Practical Project 1: Search and Optimization (3/20);
- Due Date: Monday, November 14th, 2022.
- (P2) Practical Project 2: Learning (3/20);
- Due Date: Monday, January 9th, 2023.
- To get approved at the course, a minimal mark of 5/20 should be obtained in the practical project part;
- The pratical project mark is conditioned to an individual presentation and discussion by each student;
- Written Test (F) Monday, January 9th, 2023, 09:00. Room 6.01
- Mark (M) M = (A >= 0.8) * (P * 6/20 + F * 14/20)
- Admission to Exams Students with M >= 6 are admitted to final exams
- The practical projects mark is considered in all examination epochs;
Help Practical Sheet 2 (Search Spaces): [py]
Theoretical slides (Local Search and Optimization, continuation)
Practical exercises (Optimization. Genetic Algorithms): [pdf]
Theoretical slides (Optimization, continuation)
Theoretical slides (Machine Learning: Regression/Classification): [pdf]
Practical exercises (Classification): [pdf]
Pizza Dataset: [csv]
Wines Dataset: [csv]
Auxiliary scripts (Linear Regression): [py]
Auxiliary scripts (Logistic Regression): [py]
YouTube Live Feed (Practical Works I Evaluation): [htm]
(Written Test)