In recent years Reinforcement Learning (RL) has resurfaced as one of the main drivers for AI, and in general decision making automation. RL is a powerful programming technique to enable long-term learning of software systems, being applicable to many different domains including robotics, software generation, testing, game playing, healthcare, and personalized assistants. In this course students will obtain theoretical and practical knowledge in underlying principles of RL, Markov decision processes, classic RL algorithms, and deep reinforcement learning. The course will also introduce current hot topics in advanced RL, such as transfer learning, multi objective learning, and explainability.

Natural Language Processing is a discipline of Artificial Intelligence that deals with the formulation and investigation of computational mechanisms for communication between people and machines through the use of Natural Languages. The main objective of the course is to develop a deep understanding of the algorithms available for processing linguistic information and the underlying computational properties of natural languages.

The course addresses the fundamentals and techniques of machine learning, with an emphasis on artificial neural networks and deep learning. It also deals with how to effectively use learning algorithms in a variety of domains, taking into account the nature of the problem and the available computing resources.

Course in Industrial Automation that seeks to confront the student independently to a project in Robotics.

Introductory course to optimization techniques that are usually required to be used when solving problems in various areas of engineering.

Introduce the area of computer image processing and analysis as an entry point to the applications of these techniques in real multidisciplinary problems in the biomedical area.

Understand the main statistical techniques that, together with algorithmic, are used to solve different problems of both population genetics and molecular biology.

This course focuses on understanding what knowledge is, how it is, how it is used, and how it can be computerized.

The objective of this course is to update the participants on the new applications and capabilities that the Semantic Web will make possible and the techniques that exist for their design.

The objective of this course is to provide the student with the necessary tools for the application of Machine Learning techniques to the solution of practical problems.

This course seeks to study basic and advanced concepts of probability and random variables using computational tools that allow solving problems that illustrate the concepts seen in class and introducing new topics and concepts that allow the student to know new areas of research.

This is a course with a practical approach to using tools to address problems in interdisciplinary areas, including automation, communications, Big Data, and biomedical engineering, which can generate new research topics.

After completing this course, the student is expected to know the state-of-the-art main problems of machine learning and be familiar with the theory and the computational techniques of this area. The main objective of this course is to develop research projects of enough quality to be submitted to the main international conferences in this area.

The objective of this course is to learn the theoretical and practical bases of Computer Vision, a field that focuses on the understanding of how computers gain high-level understanding from visual information.