The field of artificial neural networks has experienced rapid growth over the last 25 years and has now become a broad and autonomous scientific domain, related to the broader context of artificial intelligence and intelligent systems.

This book systematically describes the most important neural network models, starting from the simple Perceptron model of a single neuron and continuing with multi-layer Perceptron networks and the Back Propagation training algorithm, Radial Basis Function (RBF) networks, self-organizing networks such as the SOM model, linear and non-linear Hebbian learning models, support vector machines (SVM), dynamic models like the Hopfield model, and many more.

All models are categorized based on their training methods, while the reader is introduced to the broader problem of learning and self-adaptation of a computational system. The necessary mathematical background is provided for understanding the operation of the networks, without requiring advanced mathematical knowledge.

Particular emphasis is also placed on the algorithmic dimension of the models, as the most important of them are accompanied by the relevant pseudocode. Finally, the applications of neural networks constitute an important part of the book, as they represent a primary motivation for their study and development. Applications covering various areas are described, such as pattern recognition, signal and image processing, information compression, modeling, and system recognition, etc.