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

Two teaching activities are proposed: lectures and lab sessions. LECTURES The lecture sessions will be supported by slides or by any other means to illustrate the concepts explained. In these classes the explanation will be completed with examples. In these sessions, the student will acquire the basic concepts of the course. It is important to highlight that these classes require the initiative and the personal and group involvement of the students (there will be concepts that the students themselves should develop). LABORATORY SESSIONS This is a course with a high practical component, and students will attend to laboratory sessions very often. In them, the concepts explained during the lectures will be put into practice using deep learning software libraries (e.g., PyTorch). In the laboratory, machines equipped with high-performance GPUs are available and free distributed computing systems such as Google Colab will also be used.