1
برق و الکترونیک::
شدت پیکسل
This is because each image is 28×28 pixels, and each feature simply represents one pixel's intensity, from 0 (white) to 255 (black).
All it does is assign a weight per class to each pixel, and when it sees a new image it just sums up the weigh‐ ted pixel intensities to get a score for each class.
It will take as input a noisy digit image, and it will (hopefully) output a clean digit image, repre‐ sented as an array of pixel intensities, just like the MNIST images.
Notice that the classifier's output is multilabel (one label per pixel) and each label can have multiple values (pixel intensity ranges from 0 to 255).
Arguably, predicting pixel intensity is more akin to regression than to classification.
واژگان شبکه مترجمین ایران