Mong muốn để giảm thiểu thuật ngữ này có thể được dịch thành các kết nối giữa các đơn vị ức chế sự lựa chọn của các thành phố lân cận trong tương ứng với tỷ lệ với khoảng cách giữa những thành phố. Hãy xem xét thuật ngữ | CPN Data Processing 235 CPN DATA PROCESSING We are now in a position to combine the component structures from the previous section into the complete CPN. We shall still consider only the forward-mapping CPN for the moment. Moreover we shall assume that we are performing a digital simulation so it will not be necessary to model explicitly the interconnects for the input layer or the competitive layer. Forward Mapping Assume that all training has occurred and that the network is now in a production mode. We have an input vector I and we would like to find the corresponding y vector. The processing is depicted in Figure and proceeds according to the following algorithm 1. Normalize the input vector lị - 2. Apply the input vector to the x-vector portion of layer 1. Apply a zero vector to the y-vector portion of layer 1. 3. Since the input vector is already normalized the input layer only distributes it to the units on layer 2. 4. Layer 2 is a winner-take-all competitive layer. The unit whose weight vector most closely matches the input vector wins and has an output value of I. All other units have outputs of 0. The output of each unit can be calculated according to 1 llnetill llnetjll for ah j i 0 otherwise 5. The single winner on layer 2 excites an outstar. Each unit in the outstar quickly reaches an equilibrium value equal to the value of the weight on the connection from the winning layer 2 unit see Eq. . If the ith unit wins on the middle layer then the output layer produces an output vector y wu W2i . wmiY where m represents the number of units on the output layer. A simple way to view this processing is to realize that the equilibrium output of the outstar is equal to the outstar s net input yfkg z 7 Since Zj 0 unless j i then WkiZi Wki which is consistent with the results obtained in Section . This simple algorithm uses equilibrium or asymptotic values of node activities and outputs. We thus avoid the need to solve numerically all
