Deep Learning is a new field within Machine Learning. In the past 4 years researchers have been training neural networks with a very large number of layers. Algorithms are learning how to classify images to a much greater accuracy than before: you can give them an image of a cat or a dog and they will be able to tell the difference. Traditionally this has been nearly impossible for computers but easy for humans.
Deep Learning algorithms are trained by giving them a huge number of images, and telling them what object is in each image. Once it has seen (e.g.) a hundred types of dog heads 1000 times from a hundred angles, it has been 'trained'. Now you can give it new images and it will spot dog heads within the images, or tell you that there are none at all. It also can say how unsure it is.
It was always hard to tell what the algorithms were 'seeing' or 'thinking' when we gave them new images. So in June 2015 Google Engineers released a method for visualising what the algorithms saw.. Towards the end of June 2015 they released their code, so people could see what the trained neural networks were seeing on any image they wanted.
We created this sub to put these images in. It also is fast becoming the place to discuss techniques/methods and try out totally new ideas, such as video