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 : Three-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 from input layer to hidden layer
• b_i² is the bias for hidden layer
• z_i² is the input for hidden layer
• a_i² is the output for hidden layer
• w_{i j}³ is the weight from hidden layer to output layer
• b_i³ is the bias for output layer
• z_i³ is the input for output layer
• a_i³ is the output for output layer