Techniques and Tools for Artificial Intelligence: Neural Networks. Examples with Python and R

Artificial intelligence (AI) is a branch of computer science that seeks to develop systems capable of performing tasks that traditionally require human intelligence. Artificial Intelligence combines mathematical algorithms and Machine Learning, Deep Learning and Big Data techniques to extract the knowledge contained in data and present it in a comprehensible and automatic way. In this book, the use of neural networks for supervised and unsupervised learning is discussed in depth. Regarding supervised learning, the most common architectures are considered, such as Multilayer Perceptron, Radial Basis Network, ADALINE Networks, HOPFIELD Networks, Probabilistic Networks, Linear Networks, Generalised Regression Networks, LVQ Networks, Linear Networks and Networks for Regression Model Optimisation. In this section of supervised analysis, special attention should be paid to Neural Networks for Time Series Prediction such as the LSTM Network, GRU Networks, Recurrent Neural Networks RNN, NARX Networks, NNAR Networks and, in general, Dynamic Neural Networks. Unsupervised learning develops Pattern Recognition and Cluster Analysis Networks such as KOHONEN Networks (SOM Self-Organising Maps), Pattern Recognition Networks, Autoencoder Neural Networks, Transfer Learning Networks, Anomaly Detection Networks and Convolutional Neural Networks.