Checking date: 29/05/2024

Versión en español

Course: 2024/2025

Deep learning
(19206)
Master in Applied Artificial Intelligence (Plan: 475 - Estudio: 378)
EPI


Coordinating teacher: MARTÍNEZ OLMOS, PABLO

Department assigned to the subject: Signal and Communications Theory Department

Type: Electives
ECTS Credits: 3.0 ECTS

Course: 1º
Semester: 1º



Requirements (Subjects that are assumed to be known)
The students are expected to have basic knowledge of - Calculus - Programming skills - Numerical optimization
Objectives
The fundamental objective of this subject is for the student to know and learn to use learning schemes based on advanced neural networks, with special emphasis on computer vision applications and treatment of audio signals, and the adjustment of probabilistic models for the generation of artificial data.
Skills and learning outcomes
Link to document

Description of contents: programme
1. Probabilistic modeling with deep networks: VAEs 2. Probabilistic modeling with deep networks: GANs 3. Implicit representation models 4. Segmentation and object detection with deep networks. 5. Deep voice and audio processing
Learning activities and methodology
MD1 Practical classes MD3 Practical classesatorio MD3 Laboratory practices MD5 Group work Individual exams and tutoring hours
Assessment System
  • % end-of-term-examination 30
  • % of continuous assessment (assigments, laboratory, practicals...) 70

Calendar of Continuous assessment


Basic Bibliography
  • Cristopher Bishop. Pattern Recognition and Machine Learning. Springer. 2006
  • Ian Goodfellow and Yoshua Bengio and Aaron Courville. Deep Learning. MIT Press. 2017
  • Kevin Murphy. Machine Learning A Probabilistic Perspective. MIT Press. 2012

The course syllabus may change due academic events or other reasons.