learned to sort images into categories even better than humans in some cases. If there’s one method out there that justifies
the hype, it is CNNs.
What’s especially cool about them is that they are easy to understand, at least when you break them down into their basic
parts. I’ll walk you through it. There's a video that talks through these images in greater detail. If at any point you get a bit
lost, just click on an image and you'll jump to that part of the video.
X's and O's
To help guide our walk through a Convolutional Neural Network, we’ll stick with a very simplified example: determining
whether an image is of an X or an O. This example is just rich enough to illustrate the principles behind CNNs, but still
simple enough to avoid getting bogged down in non-essential details. Our CNN has one job. Each time we hand it a picture,
it has to decide whether it has an X or an O. It assumes there is always one or the other.
A naïve approach to solving this problem is to save an image of an X and an O and compare every new image to our
exemplars to see which is the better match. What makes this task tricky is that computers are extremely literal. To a
computer, an image looks like a two-dimensional array of pixels (think giant checkerboard) with a number in each position.
In our example a pixel value of 1 is white, and -1 is black. When comparing two images, if any pixel values don’t match, then
the images don’t match, at least to the computer. Ideally, we would like to be able to see X’s and O’s even if they’re shifted,
shrunken, rotated or deformed. This is where CNNs come in.
Features
评论1
最新资源