MACHINE LEARNING TECHNIQUES AND TOOLS FOR ARTIFICIAL INTELLIGENCE. NEURAL NETWORKS VIA R AND PYTHON

Artificial Intelligence combines mathematical algorithms and techniques from Machine Learning, Deep Learning, and Big Data to extract knowledge contained in data and present it in an understandable and automated way. Neural networks play a crucial role in all these disciplines. This book delves into the use of neural networks for supervised and unsupervised learning. Regarding supervised learning, the most common architectures are considered, such as Multilayer Perceptrons, Radial Basis Networks, ADALINE Networks, HOPFIELD Networks, Probabilistic Networks, Linear Networks, Generalized Regression Networks, LVQ Networks, Linear Networks, and Networks for Regression Model Optimization. In this section on supervised analysis, neural networks for time series prediction, such as LSTM Networks, GRU Networks, Recurrent Neural Networks (RNN), NARX Networks, NNAR Networks, and, in general, Dynamic Neural Networks, deserve special attention. Regarding unsupervised learning, pattern recognition and cluster analysis networks are developed, such as KOHONEN networks (self-organizing maps, SOMs), autoencoder neural networks, transfer learning networks, anomaly detection networks, and convolutional neural networks. For each type of neural network, examples are presented with optimal syntax in R and Python.