2.- Specialization Module

M04 - Intelligence in Data Science

This subject aims to provide the student with the basic knowledge on the different methodologies and techniques in automatic learning (machine learning) to apply them critically to real problems, including text and web mining. A second practical goal is to provide the standard skills and tools needed to autonomously analyze data projects.

M04-01 - Machine Learning I

M04-02 - Machine Learning II

M04-03 - Semantics, Linked Data, Text Data Mining

1. Neural networks. Multilayer and recurrent topologies

2. Iterative learning algorithms (backprop).

3. Reservoirs and techniques of random projection.

4. Extreme Learning Machines.

5. Challenges in "big data" problems. Batch and online learning.

6. Deep learning. Autoencoders and convolution.

7. Technologies and packages for neural networks and deep learning.

8. Statistical learning.

9. Margins and support vectors. Support Vector Machines (SVM).

10. Kernel based methods.

11. Latent variables and EM method.

12. Hidden Markov models (HMM).

13. Bayesian learning. Probabilistic networks. Causality.

14. Models selection MCMC

15. Semantic netwoks.

16. Ontologies.

17. Ontologies learning

18. Linked data.

19. Analysis of complex networks.

20. Text and web mining