The students are expected to have studied Linear Systems. Although not mandatory, basic knowledge on Digital Image Processing is welcome.

Learning Results and their relation with course contents - To learn digital images and the spatial filtering operation over images. - To know basic concepts of Machine Learning: loss functions, regularization, hyperparameters, data augmentation, etc. - To understand deep neural networks and their training algorithms: gradient descent and back-propagation. - To learn Convolutional Neural Networks (CNN) and their most usual processing blocks/layers. - To understand, design and train CNN architectures for image classification. - To understand, design and train advanced CNN architectures to address other task of visual recognition: object detection, image captioning, image segmentation, image synthesis, etc.

C24_PAE: To apply and adapt technical knowledge and practical skills in the field of telecommunication engineering, participating in problem_solving and the development of solutions in a professional environment. KOPT_1: To know and understand in depth advanced technologies in the specific field of engineering and information and communication technologies, which constitute the state of the art in the area of study, including emerging trends and recent developments. KOPT_2: To interpret sources of scientific and technical information in order to deepen the knowledge of a specific area related to engineering and information and communication technologies. SOPT_1: Identify, assess their technical feasibility and apply advanced technological tools, methodologies and solutions used in the field of engineering and information and communication technologies to develop algorithms or systems integrating innovative and cutting_edge technologies. SOPT_2: Apply analytical and design methodologies to solve advanced problems in the field of engineering and information and communication technologies, and evaluate the performance and limitations of different technological approaches, proposing improvements and alternatives COPT_1: To conceive and develop projects that integrate advanced knowledge and provide innovative solutions in the field of engineering and information and communication technologies.

Unit 1. Basic concepts of visual recognition 1.1 Digital Images 1.2 Spatial Filtering 1.3 Part-models for object recognition Unit 2. Basic concepts of Deep learning 2.1 Machine Learning algorithms 2.2 Loss Functions 2.3 Regularization 2.4 Hyperparameters and validation 2.5 Deep Neural Networks 2.6 Gradient Decent-based learning algorithms 2.7 Backpropagation Unit 3 Convolutional Neural Networks (CNNs) for image classification 3.1 Introductions 3.2 Basic processing layers in a CNN 3.3 CNN architectures for image classification 3.4 Training a CNN for image classification: data pre-processing, data augmentation and initialization Unit 4 Deep networks for other image-related tasks: 4.1 Networks for object detection 4.2 Networks for semantic image segmentation 4.3 Networks for image synthesis: GANs, Diffusion Models, VAEs 4.4 Networks for image matching

1) Theoretical-Practical Classes - 1.03 ECTS - Theory sessions will consist of lectures utilizing slides or other audiovisual media to illustrate specific concepts. Through these sessions, students will acquire the core content of the subject. It is important to note that these classes will require initiative, as well as individual and group work from the students (e.g., certain concepts must be studied independently based on provided guidelines, or specific cases will need to be developed by the student, etc.). - The course has a significant practical component. Students are expected to attend practical classes regularly. In these sessions, concepts acquired during theory lectures will be applied using deep learning software libraries (e.g., PyTorch). The laboratories are equipped with high-performance GPU machines, and students will also utilize free distributed computing systems such as Google Colab. 2) Student Individual Work or Group Work - 1.97 ECTS