ABSTRACT
Artificial Intelligence (AI) is a subfield of computer science that models the mechanisms of intelligent human behavior (intelligence). This approach is accomplished via simulation with the help of artificial artifacts, typically with computer programs on a machine that performs calculations. This chapter divides the present AI domain into two main branches: symbolical AI and statistical Machine Learning (ML). Symbolic AI deals with symbolic representations and problem solving, and statistical is based on distributed representations. Problem-solving can be modeled by a production system that implements a search algorithm. The search defines a problem space and can be represented by a tree. Many of the ML techniques are derived from the efforts of psychologists and biologists to make more sense of human learning through computational models. Perceptron describes an algorithm for supervised learning that considers only linearly separable problems in which groups can be separated by a line or hyperplane.
