Competencies and objectives

 

Course context for academic year 2024-25

Deep learning has revolutionized artificial intelligence techniques. Thanks to these methods, it has been possible to address problems that a few years ago were considered unfeasible. This subject delves into the fundamental concepts of deep learning. It is assumed that the students have taken the subject of Machine Learning Techniques and have acquired the knowledge and skills addressed there.

 

 

Course content (verified by ANECA in official undergraduate and Master’s degrees) for academic year 2024-25

Transversal Competences

  • CT1 : Be able to lead projects related to artificial intelligence, as well as to manage work teams.
  • CT2 : Demonstrate computer and information skills in the field of artificial intelligence.
  • CT3 : Show oral and written communication skills.

 

General Competences

  • CG1 : Apply the knowledge acquired to real problems related to artificial intelligence.
  • CG10 : Be able to use engineering principles and modern computer technologies to research, design and implement new applications of artificial intelligence,
  • CG2 : Be able to develop and learn in a self-directed or autonomous way topics related to artificial intelligence.
  • CG3 : Know how to operate in multidisciplinary and/or international contexts, providing solutions from the point of view of artificial intelligence.
  • CG5 : Know how to manage the available information and resources related to artificial intelligence.
  • CG6 : Being able to adapt to environments related to artificial intelligence, fostering teamwork, creativity,
  • CG7 : To be able to adapt to the constant evolution of the discipline and to understand and apply new technical and scientific developments related to artificial intelligence.
  • CG8 : Knowing how to plan, design, develop, implement and maintain products, applications and services related to artificial intelligence, taking into account technical, economic and efficiency aspects.

 

Specific Competences

  • CE08 : In-depth knowledge of machine learning technologies, algorithms and tools (including supervised, unsupervised or reinforced learning).
  • CE23 : Ability to design and deploy end-to-end deep learning solutions for applications in different domains.

 

Basic Competences

  • CB10 : That students possess the learning skills that allow them to continue studying in a way that will be largely self-directed or autonomous.
  • CB6 : Possess and understand knowledge that provides a basis or opportunity to be original in the development and/or application of ideas, often in a research context
  • CB7 : That students know how to apply the knowledge acquired and their ability to solve problems in new or little-known environments within broader (or multidisciplinary) contexts related to their area of ¿¿study
  • CB8 : Students are able to integrate knowledge and deal with the complexity of making judgements on the basis of incomplete or limited information, including reflections on the social and ethical responsibilities associated with information which, while incomplete or limited, includes reflections on the social and ethical responsibilities linked to the application of their knowledge and judgements.
  • CB9 : Students are able to communicate their conclusions and the ultimate knowledge and rationale behind them to specialist and non-specialist audiences in a clear and unambiguous way.

 

 

 

Learning outcomes (Training objectives)

- Understand the fundamental concepts of deep learning.

- Train a deep neural network by selecting the most appropriate characteristics of the same depending on the type of problem and optimising the hyperparameters.

- Describe the main architectures used in deep learning, as well as the most typical applications.

- Identify the most appropriate type of deep learning algorithm for various types of problems in different domains.

- Implement deep learning algorithms using different tools.

 

 

Specific objectives stated by the academic staff for academic year 2024-25

Deep learning is a type of artificial intelligence that allows us to train a computational model capable of solving complex tasks using raw data. In this subject we will work with advanced deep learning models that have a large number of parameters such as deep convolutional models or recurrent models, among others. The main objectives are:

- To know the main deep neural architectures.
- To understand the strategies to train large models, such as data augmentation or design of specific loss functions.
- To understand different training strategies such as transfer learning, self-supervised learning, deep reinforcement learning, zero/few-shot learning, etc.

 

 

General

Code: 43509
Lecturer responsible:
PERTUSA IBAÑEZ, ANTONIO JORGE
Credits ECTS: 4,50
Theoretical credits: 0,90
Practical credits: 0,90
Distance-base hours: 2,70

Departments involved

  • Dept: INFORMATION TECHNOLOGY AND COMPUTING
    Area: COMPUTER ARCHITECTURE
    Theoretical credits: 0,3
    Practical credits: 0,3
  • Dept: LANGUAGES AND COMPUTING SYSTEMS
    Area: LANGUAGES AND COMPUTING SYSTEMS
    Theoretical credits: 0,6
    Practical credits: 0,6
    This Dept. is responsible for the course.
    This Dept. is responsible for the final mark record.

Study programmes where this course is taught