Description

Theory
2

Laboratory
2

Instructors

Carlos Ramos

Contents

1 - Neurons and Neuronal Coding
2 - Artificial Neurons
3 - Perceptron and Artificial Neural Networks
4 - Learninig and Backpropagation
5 - Data Sets, Training, Validation and Testing of Neural Networks
6 - Deep Learning
7 - Convolutional Neural Networks
8 - Recurrent and Recursive Neural Networks and Transformers
9 - Hardware and Architectures for Deep Learning
10 - Libraries and Frameworks for Deep Learning
11- Complements of Neural Networks
12- Computer Vision with Deep Learning and Generative AI
13- Current challenges of neural networks and deep learning
14- Big Data Processing

Learning Outcomes

CO1- Become aware, understand and apply the concepts of neuronal coding, models of neurons and artificial neural networks (ANN), training, validation and testing of ANN, deep learning models and their hardware, software platforms and applications, it is also intended to learn the concept of big data.
CO2- Knowing and understanding a real problem of medium or high complexity and analyzing, investigating, designing, implementing, experimenting, reviewing, testing, synthesizing and evaluating in order to solve this problem using the methods presented in the course
CO3- Develop transversal skills related to teamwork in response to challenges (AI Challenges4Teams)