Checking date: 14/01/2024

Versión en español

Course: 2023/2024

Deep Learning
(19277)
Master in Machine Learning for Health (Plan: 480 - Estudio: 359)
EPI


Coordinating teacher: MARTÍNEZ OLMOS, PABLO

Department assigned to the subject: Signal and Communications Theory Department

Type: Electives
ECTS Credits: 6.0 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 objective of the course is the description and implementation of the fundamental models and architectures in deep learning, covering problems of different kinds and advanced methodologies.
Skills and learning outcomes
Link to document

Description of contents: programme
Neural networks and backpropagation. Deep networks: optimization and regularization for massive data. Deep architecture and methods for spatially correlated data. Deep architectures and methods for sequences. Deep attention models and transformers. Representation learning. Generative deep neural networks.
Learning activities and methodology
AF3 Theoretical practical classes AF4 Laboratory practices AF5 Tutorials AF6 Team work AF7 Student individual work AF8 Partial and final exams Activity code total hours number presencial hours number % Student Presence AF3 134 134 100% AF4 42 42 100% AF5 24 0 0% AF6 120 0 0% AF7 248 0 0% AF8 16 16 100% SUBJECT TOTAL 600 184 30,66%
Assessment System
  • % end-of-term-examination 0
  • % of continuous assessment (assigments, laboratory, practicals...) 100
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.