A Hybrid Approach Based on Genetic Algorithm and Particle Swarm Optimization to Improve Neural Network Classification

2. Neural Network

Artificial neural network is an important part of artificial intelligence (Wang & Li, 2010). In addition, it is a mathematical model that mimics the structure and function of a human brain (Chogumaira & Hiyama, 2009; Jia & Zhu, 2009). The human brain consists of billions of neurons that are connected, communicating with each other by the use of electrical signals (Haron et al., 2012). ANN, like a human brain, consists of simple processing units, which are called neurons, organized in layers and connected to each other through connection weights and threshold value for information transmission and processing. The weights and thresholds are adjusted automatically in the learning process (Zhang et al., 2009; Shenglong & Tonghui, 2012). The concept of learning from inputs to outputs in ANN is similar to the way that the human brain learns from experience (Miao et al., 2010). There are many different types of ANN structures. One common structure is the Multi-Layer Perceptron (MLP), which is a feed forward type of the neural network. The typical MLP network model consists of a group of neurons with three categories, which are input neurons, hidden neurons, and output neurons. Each neuron is in one layer and is connected with all neurons of the adjusted layer. The operation of a typical MLP network can be divided into two phases, which are training and testing phases. The MLP network must be trained for its specific purpose using learning algorithms like backpropagation algorithm. After the step of training, the MLP network can be used to generate the outputs (Al-Shareef & Abbod, 2010).