This subject is based on the knowledge given in the previous subject of the same Masters' programme: - Data analytics in IC4.0

The objectives of the course are: 1. To deepen the knowledge of machine learning models that allow information to be converted into knowledge in connected industry 4.0 environments. 2. To acquire skills in the use of Python tools to deploy the learned models in the resolution of specific cases. 3. To know the capabilities and limitations that machine learning model execution environments present.

The contents of the course are divided into the following program sections: - Pre-processing of data: Techniques, methods, tools and applications for detection of outliers - Programming and tools for data analysis - Analysis of data in the cloud - Advanced classification methods with SVM and shallow neural networks - Advanced classification and regression with deep learning methods. Restricted Boltzmann machines and Autoencoders. - Advanced classification and regression with deep learning methods. Deep recurrent and convolutional neural networks. - Data management in the cloud. Tools and architectures.

The distribution of hours by training activity is as follows: AF1 Theoretical class (12 hours) AF2 Practical classes (6 hours) AF4 Laboratory practices (3 hours) AF5 Tutorials (2 hours) AF6 Group work (25 hours) AF7 Individual student work (25 hours) AF8 Part-time and final exams (2 hours) The training methodologies used are: MD1 Class presentations by the professor with the support of computer and audiovisual media, in which the main concepts of the subject are developed and the bibliography is provided to complement the students' learning. MD2 Critical reading of texts recommended by the professor of the subject: articles, reports, manuals and/or academic articles to expand and consolidate the knowledge of the subject. MD3 Resolution of practical cases and problems posed by the professor individually and in groups in relation to the connected industry MD4 Presentation and discussion in class, under the moderation of the professor, of topics related to the content of the subject, as well as practical cases