Master Artificial Intelligence Algorithms

Recommended Prerequisites

Python programming; Good English reading, writing and speaking skills; Mathematics and statistics.

Teaching Methods

During the lectures (T) the concepts, the theories, the algorithms will be presented and discussed. In the lab classes (PL) students will consolidate what was learned in T. The practical assignments will be done under the supervision of the teacher. Grading will be based on two components: (1) projects involving the techniques and/or a practical problem; (2) a written exam to assess students' knowledge about the subject.

Learning Outcomes

The curricular unit aims to give an encompassing view of Artificial Intelligence (AI). Following Pedro Domingo's classification, we consider five main tribes of AI algorithms. For each tribe, we introduce the area, analyze some of its main topics, indicate applications, and provide a general overview of the field.

 

By the end of the course, the student will have a comprehensive view of the field of AI, including the main approaches, the possibilities, limitations and open challenges in the field. They will also be able determine what approaches are adequate for real-world problems that require AI.

 

The main competencies to be developed are:

Instrumental – analysis and synthesis, problem-solving

Personal – critical thinking

Systemic - practical application of the theoretical knowledge; research

 

The secondary competencies are:

Instrumental – organizing and planning

Personal – work in teams

Systemic – autonomous learning; creativity

Work Placement(s)

No

Syllabus

1. Introduction to Artificial Intelligence

            1.1 What is Artificial Intelligence?

            1.2 History and Evolution of AI

            1.3 The Five Tribes

            1.4 Problem Classes

            1.5 Applications of AI

2. Symbolic AI

            2.1 Introduction to Symbolic AI

            2.2 Knowledge Representation and Reasoning

            2.3 Applications of Symbolic AI

            2.4 Overview of the area

3. Connectionist AI

            3.1 Introduction to Connectionist AI

            3.2 Multilayer perceptron (MLP) networks

            3.3. Applications of Connectionist AI

            3.4 Overview of the Area

4. Bayesian AI

            4.1 Introduction to Bayesian AI

            4.2 Probabilistic Models and Inference

            4.3 Bayesian Networks

            4.4 Applications of Bayesian AI

            4.5 Overview of the Area

5. Analogy-Based AI

            5.1 Introduction to Analogy-Based AI

            5.2 Clustering

            5.3 Applications of Analogy-Based AI

            5.4 Overview of the Area

6. Evolutionary AI

            6.1 Introduction to Evolutionary AI

            6.2 General Evolutionary Algorithm

            6.3 Applications of Evolutionary AI

            6.4 Overview of the Area

Assessment Methods

Assessment
Project: 50.0%
Exam: 50.0%

Bibliography

 

Domingos, P. (2017). The master algorithm. Penguin Books.

Russell, S. J. 1., Norvig, P., & Davis, E. (2010). Artificial intelligence: a modern approach. 3rd ed. Upper Saddle River, NJ, Prentice Hall.

Poole, D. L., & Mackworth, A. K. (2017). Artificial Intelligence: Foundations of Computational Agents (2nd ed.). Cambridge University Press.

Negnevitsky, M. (2005). Artificial Intelligence: A Guide to Intelligent Systems. Pearson Education