-If you let each pixel vary independently, the space of possible 1024x1024 images is 1,048,576-dimensional, but the vast hypermajority of those images aren't photorealistic human faces. Letting each pixel vary independently is the wrong way to think about it: changing the lighting or pose changes can change a lot of pixels in what we would regard as images of "the same" face. Instead, our machine-learning algorithms learn a [compressed](https://www.lesswrong.com/posts/ex63DPisEjomutkCw/msg-len) representation of what makes the tiny subspace (relative to images-in-general) of _faces in particular_ similar to each other, and that [latent space](https://towardsdatascience.com/understanding-latent-space-in-machine-learning-de5a7c687d8d) is a lot smaller—say, 512 dimensions.
+If you let each pixel vary independently, the space of possible 1024x1024 images is 1,048,576-dimensional, but the vast hypermajority of those images aren't photorealistic human faces. Letting each pixel vary independently is the wrong way to think about it: changing the lighting or pose can change a lot of pixels in what humans would regard as images of "the same" face. So instead, our machine-learning algorithms learn a [compressed](https://www.lesswrong.com/posts/ex63DPisEjomutkCw/msg-len) representation of what makes the tiny subspace (relative to images-in-general) of _faces in particular_ similar to each other, and that [latent space](https://towardsdatascience.com/understanding-latent-space-in-machine-learning-de5a7c687d8d) is a lot smaller—say, 512 dimensions.