3-2. parameter calculation

Taking the differences value between the output and the supervisor, the neural network parameter will change simultaneously until the output are as same as supervisor signal.

Fig 3 : 4-layer model with parameter

Figure above shows the neural network model with each parameter in its respective layer. The definition of each parameter are as describe below:

• k_i is the input signal
• w_{i j}² is the weight between i-th output of a input layer and j-th input of hideen layer 1.
• b_i² is the i-th bias of hideen layer 1
• z_i² is the i-th input of hideen layer 1
• a_i² is the i-th output of hideen layer 1
• w_{i j}³ is the weight between i-th output of hideen layer 1 and j-th input of hideen layer 2.
• b_i³ is the i-th bias of hideen layer 2
• z_i³ is the i-th input of hideen layer 2
• a_i³ is the i-th output of hideen layer 2
• w_{i j}⁴ is the weight between i-th output of hideen layer 2 and j-th input of a output layer.
• b_i⁴ is the i-th bias of a output layer
• z_i⁴ is the i-th input of a output layer
• a_i⁴ is the i-th output of a output layer