MATLAB enables the design of artificial intelligence models through three essential pillars: Machine Learning, Deep Learning and Data Science. Using MATLAB, engineers and other experts have deployed thousands of machine learning applications. Automated machine learning (AutoML) generate automatically functionalities from training data and optimize models using hyperparameter fitting techniques such as Bayesian optimization. Use specialized functionalities extraction techniques, such as wavelet dispersion for signal or image data, and functionalities selection techniques, such as neighbor component analysis (NCA) or sequential functionalities selection. Deep Learning is a subset of machine learning based on artificial neural networks. The process of this learning is called deep because this network structure consists of having multiple inputs, outputs and hidden layers. Each layer contains units that transform the input data into information, and in this way, the next layer can use it for a certain predictive task. In this way, a machine can learn through its own data processing. MATLAB has the tool Neural Network Toolbox (Deep Leraning toolbox fron release 18) that provides algorithms, functions, and apps to create, train, visualize, and simulate neural networks. You can perform classification, regression, clustering, dimensionality reduction, time-series forecasting, and dynamic system modeling and control. This book develops the neural network architectures used in Deep Learning.
