This course gives an introduction to the basic neural network architecture, algorithm and theory. Our emphasis is the algorithm analysis of neural networks, implementation technology and their application to actual problem. We add the artificial neural network modeling based on SIMULINK and artificial neural network design based on GUI software in this course. All efforts have been made to present material in clear and consistent manner so that it can be read and applied with ease.

There are two sections in this course, which consists of 13 chapters. And there are 40 lectures in the course. Among them, 27 lectures are theoretical teaching and 13 lectures are practical teaching.

The first section is the foundation of neural network (Chapter 1~3), which mainly includes the theoretical basis of biological neural network, the review of artificial neural network and the mathematical foundation of artificial neural network. The architecture of neurons and electrical activity are introduced from the perspective of biological neural networks, and the neural network mechanism of information transmission and information memory is explained in Chapter 1. The development, characteristics and applications of artificial neural network is given in Chapter 2. The neuron model is presented in Chapter 3.

The second section is artificial neural network theory (Chapter 4~13), which mainly includes Perceptron, BP neural network, RBF neural network, ADALINE neural network, HOPFIELD neural network, the deep convolutional neural network, the generative adversarial network, ADABOOST neural network, ELMAN neural network and SOFM neural network. In order to enhance the depth of theoretical learning, the neural network algorithms are illustrated in successive iteration method, and we provide some detailed examples for all key concepts and applications.