In this course, three of the most widely used tools in the field of artificial intelligence, including: optimization with genetic algorithms, neural networks, and fuzzy inference engines, are presented.
Learning these three tools is very effective in understanding the concepts of intelligence. Also, these three tools are widely used in interaction with other intelligent and specialized tools such as: image processing, deep learning, data mining, etc.
This chapter examines the common concepts and terms in optimization problems and examines the various forms of optimization problems in the form of simple examples.
In the second chapter, the toolbox and commands used in MATLAB software are explained. Inputs and outputs as well as adjustment parameters are introduced in the toolbox. Multi-objective optimization issues are also explained.
In the third chapter, the issue of the neural networks is discussed. Basic concepts, neurons, weights and biases, activation function, forward network, network error, backward network, and correction of coefficients are examined in the form of a comprehensive example.
In the fourth chapter, the commands used in building the network from the beginning to training and validating the network are examined. This section focuses more on how to use the MATLAB toolkit for more complex examples.
Chapter 5 introduces the concepts used in fuzzy inference engines. Concepts such as input and output variables, membership functions, fuzzy rules, and instructions used are explained with examples.
In the last chapter, first, the method of using the fuzzy inference engine in the form of a graphical interface is examined. Then the application of fuzzy logic in ANFIS neurophase prediction systems is discussed.