News for hackers. Stuff that matters.

limefrog

Ever seen "word2vec"? Each word is embedded in a high-dimensional "concept" space, where words that are similar to each other will be close by.

A CNN does this for localized sections of the images. Each layer looks over a wider area of the original image (because of the convolution) and embeds the "concepts" in that area of the image in a higher-dimensional space than the layer before it.