Đây là một hệ thống phương trình tuyến tính có thể được xem như là: 2 01:00 2m i D1 cos P! 0 xi / 6 1:00 | Artificial Neural Networks 73 This is a system of linear equations that can be viewed as 2m pr 1cos p X i 2 Pi 1 cos 0Xi pm l cos 0X cos p 0X _ P 1cos p 0Xi cos p Xi 2 Er 1cos p 0Xi . pr 1cos2 p 0Xi ao ai an - ỉĩì Ei 1 yi P 1 yi cos 0Xi P 1 yi cos p 0Xi Then we can solve this system for all coefficients. At this point p is the number of neurons that we want to use in the T-ANN . In this way if we have a data collection of the input output desired values then we can compute analytically the coefficients of the series or what is the same the weights of the net. Algorithm is proposed for training T-ANNs eventually this procedure can be computed with the backpropagation algorithm as well. Algorithm T-ANNs Step 1 Determine input output desired samples. Specify the number of neurons N. Step 2 Step 3 Evaluate weights Ci by LSE. STOP. Example . Approximate the function f X X2 3 in the interval 0 5 with a 5 neurons b 10 neurons c 25 neurons. Compare them with the real function. Solution. We need to train a T-ANN and then evaluate this function in the interval 0 5 . First we access the VI that trains a T-ANN following the path ICTL ANNs T-ANN . This VI needs the x-vector coordinate y-vector coordinate and the number of neurons that the network will have. In these terms we have to create an array of elements between 0 5 and we do this with a stepsize of by the . This array evaluates the function X2 3 with the program inside the for-loop in Fig. . Then the array coming from the is connected to the X pin of the and the array coming from the evaluated x-vector is connected to the y pin. Actually the pin n is available for the number of neurons. Then we create a control variable for neurons because we need to train the network with a different number of neurons. 74 3 Artificial Neural Networks Fig. Block diagram of the training and evaluating T-ANN Fig. Block diagram for plotting the .
