Ficha

Versión en español

Course: 2022/2023

Neural Networks

(19203)

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 is that the student learns to design decision machines based on neural networks for basic learning problems in tabular and multimedia data, paying special attention to regularization and validation techniques. Likewise, the student will learn to use automatic differentiation software packages for model training and experimental simulation.

Skills and learning outcomes

Link to document

Description of contents: programme

1. Neural Networks and Backpropagation 2. Regularization and explainability 3. Architectures for high-dimensional correlated data: images, time series and graphs

Learning activities and methodology

Theoretical practical classes Laboratory practices Tutorials Team work Student individual work Partial and final exams

Assessment System

The continuous evaluation will consist of partial exams, practicals and programming projects and presentation of works.

% 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.