K10_IA: To know the fundamentals of artificial neural networks and deep learning models. S7_IA: To apply machine learning methods to classification, regression, unsupervised analysis, and reinforcement learning problems on audiovisual data and acoustic systems. S8_IA: To apply artificial neural networks and deep learning models to develop services, applications and telecommunication systems that incorporate audiovisual data and acoustic signals. C12_ETEGISA1: Ability to construct, develop and manage telecommunication networks, services, processes and applications, such as systems for capture, analog and digital processing, codification, transport, representation, processing, storage, reproduction, audiovisual services presentation and management and multimedia information C14_ETEGISA3: Ability to develop projects for locales and installations, aimed at production and recording of audio and video signals. C16_ETEGISA5: Ability to create, codify, manage, disseminate and distribute multimedia content, in accordance with criteria of usability, accessibility of audiovisual services, diffusion and interactivity

1. Image formation in human visual system and digital cameras: photometric and geometric models 2. Local descriptors and invariants 3. Motion estimation and optical flow 4. Stereoscopic vision and structure from motion 5. Video object tracking 6. Image registration: rigid and deformable 7. Image classification with deep neural networks 8. Semantic image segmentation and object detection with deep learning 9. Generative AI for image and video synthesis and FX processing 10. Video analysis and understanding with IA