DEEP LEARNING TOOLS: NEURAL NETWORKS USING MATLAB

MATLAB enables the design of artificial intelligence models through three essential pillars: Machine Learning, Deep Learning and Data Science. MATLAB facilitates data science tasks with tools to access and preprocess data, create predictive and machine learning models, and deploy models in enterprise IT systems. Using MATLAB, engineers and other experts have deployed thousands of machine learning applications. 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. Neural networks theory is inspired from the natural neural network of human nervous system. Is possible define a neural network as a computing system made up of a number of simple, highly interconnected processing elements, which process information by their dynamic state response to external inputs.An Artificial Neural Network (ANN) is an information processing paradigm that is inspired by the way biological nervous systems, such as the brain, process information. The key element of this paradigm is the novel structure of the information processing system. It is composed of a large number of highly interconnected processing elements (neurones) working in unison to solve specific problems. ANNs, like people, learn by example. An ANN is configured for a specific application, such as pattern recognition or data classification, through a learning process. Learning in biological systems involves adjustments to the synaptic connections that exist between the neurones. This is true of ANNs as well.This book develops the architecture of the most important neural networks: Perceptron, ADALINE, Radial Basis, Hopfield, Probabilistic, Generalized regression and LVQ neural Networks. It also presents practical examples of the different architectures of neural networks.