tailieunhanh - neural networks algorithms applications and programming techniques phần 4

chúng tôi sẽ thảo luận về cấu trúc dữ liệu sẽ được sử dụng trong suốt phần còn lại của văn bản này làm cơ sở cho các thuật toán mô phỏng mạng được trình bày như là một phần mỗi vì nó liên quan đến một tổng hợp của tất cả các kết quả đầu ra, nó có một nhân vật khá toàn cầu, không giống như hai nhiệm kỳ đầu tiên, | 112 Backpropagation Automatic Paint QA System Concept. To automate the paint inspection process a video system was easily substituted for the human visual system. However we were then faced with the problem of trying to create a BPN to examine and score the paint quality given the video input. To accomplish the examination we constructed the system illustrated in Figure . The input video image was run through a video frame-grabber to record a snapshot of the reflected laser image. This snapshot contained an image 400-by-75 pixels in size each pixel stored as one of 256 values representing its intensity. To keep the size of the network needed to solve the problem manageable we elected to take 10 sample images from the snapshot each sample consisting of a 30-by-30-pixel square centered on a region of the image with the brightest intensity. This approach allowed us to reduce the input size of the BPN to 900 units down from the 30 000 units that would have been required to process the entire image . The desired output was to be a numerical score in the range of 1 through 20 a 1 represented the best possible paint finish a 20 represented the worst . To produce that type of score we constructed the BPN with one output unit that unit producing a linear output that was interpreted as the scaled paint score. Internally 50 sigmoidal units were used on a single hidden layer. In addition the input and hidden layers each contained threshold Ớ units used to bias the units on the hidden and output layers respectively. Once the network was constructed and trained 10 sample images were taken from the snapshot using two different sampling techniques. In the first test the samples were selected randomly from the image in the sense that their position on the beam image was random in the second test 10 sequential samples were taken so as to ensure that the entire beam was In both cases the input sample was propagated through the trained BPN and the score produced as .