Programming. First year, first semester Linear Algebra. First year, first semester Statistics. Second year, second semester

The aim of this course is that the student knows and develops computational learning techniques in the context of Artificial Neural Networks in addition designing and implementing applications and systems that use them, including those dedicated to automatic extraction of information and knowledge from data.

1. Introduction 1.1. Basics of Neural Networks 1.2. History of Neural Networks 1.3. First computational models 2. Perceptron 2.1. Architecture and parameters 2.2. Learning algorithm 2.3. Learning procedure 3. Non supervised neural models 3.1. Basics of non supervised learning 3.2. Clustering 3.3. Self organizing maps 3.4. Different non supervised models 4. Recurrent Neural Networks 4.1. Basics of Recurrent Neural Networks 4.2. Learning in recurrent networks 4.3. Recurrent models 5. Convolutional Neural Networks 5.1. Autoencoders 5.2. Image processing task 5.3. Fundamentals of Convolutional networks 5.4. Architecture in convolutional networks 5.5. Advance Neural Networks models 6. Neural networks in practice 6.1. Treatment and pre-processing of learning data 6.2. Generation and validation of neural network models 6.3. Hyperparameter tuning 6.4. Model comparison

Theory: Lectures will be focused on teaching all concepts related to neural networks, so that students acquire knowledge on artificial neural networks necessary for professional development and they will be carried out in synchronous on-line mode. 3 ECTS Practical sessions (small groups): The practical classes will be developed so that, in a supervised way, students learn to solve real problems with artificial neural networks. The practices will be carried out in groups of 2 students, enhancing teamwork (Soft-skill: teamwork). 3 ECTS The weekly planification shows the exact distribution for each activity.