Different quotes for neural net

That’s the magic of deep learning: turning meaning into vectors, then into geo- metric spaces, and then incrementally learning complex geometric transformations that map one space to another. All you need are spaces of sufficiently high dimension- ality in order to capture the full scope of the relationships found in the original data. The whole process hinges on a single core idea: that meaning is derived from the pair- wise relationship between things (between words in a language, between pixels in an image, and so on) and that these relationships can be captured by a distance function. But note that - (François Chollet , Deep Learning with Python)