Artificial Intelligence

Not Applicable.

The teaching methods (ME) to be used are balanced between traditional and active and are as follows:
ME1 Content exposure by the teacher (compatible with learning objectives 1 to 7)
ME2 Test the contents learned by students (compatible with learning objectives 1 to 7)
ME3 Student Problem Solving (Compatible with Learning Objectives 4 to 8)
ME4 Interaction and sharing of ideas by students (compatible with learning objective 8)
ME5 Development of critical thinking by students (compatible with learning objectives 7 and 8)
ME6 Research done by students (compatible with learning objectives 4 to 8)
ME7 Student-made creation (compatible with learning objectives 8)
The curricular unit is based on theoretical-practical classes. The teaching methods (ME) to be used are balanced between traditional and
active.
Classes include the presentation of concepts and methodologies and proceeding with their discussion, as well as the demonstration of the
resolution of applied problems. In the classes concepts and methodologies are presented, contents are discussed and problem solving is
demonstrated. The content is taught and discussed in a classroom environment.
In addition to the traditional expository method, the methodology will include project-based learning (PBL). As the name implies, an active
learning methodology that aims to associate learning with doing. This method is based on the construction of knowledge collectively,
moving away from the conventional classroom model where the teacher teaches a subject and the students show how much they have
learned from a final evaluative activity. The project that is proposed to be developed, preferably carried out in a group, aims to go through
the various phases of an artificial intelligence project.

The main learning objectives (AO) defined are the following:
LO1 – Know the principles of artificial intelligence
LO2 – Know the principles of knowledge representation and inference
LO3 – Understand the working principles of expert systems
LO4 – Know the main tasks and activities of artificial intelligence
LO5 – Know the main techniques and algorithms of artificial intelligence
LO6 – Knowing some tools and technologies and knowing how to use some of them
LO7 – Know how to evaluate the quality of solutions and know how to validate these solutions
LO8 – Know how to apply in a practical project some of the main concepts and approaches learned
The teaching methods (ME) to be used are balanced between traditional and active and are listed in Topic 8.

1 Introduction to Artificial Intelligence
1.1 History of Artificial Intelligence
1.2 Principles of Artificial Intelligence, Machine Learning and Deep Learning
1.3 Weak, strong and superintelligence Artificial Intelligence
1.4 Discovery of Knowledge in Databases and Data Mining
2 Knowledge and Inference
3 Expert Systems
4 Main tasks and activities
4.1 Predictive (or supervised) activities
4.2 Descriptive (or unsupervised) activities
4.3 Prescriptive Activities
5 Main techniques and algorithms
5.1 Induction of Decision Trees
5.2 Artificial Neural Networks
5.3 Genetic Algorithms
5.5 Rule Induction
5.5 Fuzzy Sets
5.6 Bayes Networks
5.7 Other techniques and algorithms
6 Tools and Technologies
7 Quality and Validation of solutions

The knowledge assessment for this course unit can be carried out in two ways: Continuous Evaluation or By Exam.

a) Continuous Assessment

Continuous assessment occurs during the academic term and is concluded on the last day of classes, comprising a practical project (ACPP) and two written tests (AC1F and AC2F).
- The practical project must be carried out in groups of 2-3 members. The evaluation of the project is subject to a presentation and defence.
- The two written tests must be taken individually.
- A minimum mark of 7 out of 20 in each written test is required to pass.
- A minimum attendance of 70% of classes is mandatory.
- The scheduling of both tests, the submission of the project, and its presentation will be announced in class in due time.
- The final grade is rounded to the nearest whole number according to the following calculation formula:
                                                       Final Grade = 30% x AC1F + 30% x AC2F + 40% x ACPP

If the minimum requirements are not met, the final grade will be 5 out of 20.

b) By Exam

The By Exam assessment occurs during the regulated examination periods, comprising a practical project (PP) and a written exam (EE).
- The practical project must be carried out in groups of 2-3 members. The evaluation of the project is subject to a presentation and defence.
- The written exam must be taken individually.
- The scheduling of project presentations and written exams is the date defined in the regulated examination period in which the student intends to be assessed.
- The final grade is rounded to the nearest whole number according to the following calculation formula:
                                                       Final Grade = 60% x EE + 40% x PP

All information regarding the constitution of project groups, project topics, scheduling of submissions, and defences of the projects will be officially announced through the Nónio platform.

In both of the mentioned methodologies, all components are mandatory. Failure to complete any component will result in a grade of 0 (zero) for that component.

NAO