guardian | What do machines dream of? New images released by Google give us one potential answer: hypnotic landscapes of buildings, fountains and bridges merging into one.
The pictures, which veer from beautiful to terrifying, were created by the company’s image recognition neural network, which has been “taught” to identify features such as buildings, animals and objects in photographs.
They were created by feeding a picture into the network, asking it to
recognise a feature of it, and modify the picture to emphasise the
feature it recognises. That modified picture is then fed back into the
network, which is again tasked to recognise features and emphasise them,
and so on. Eventually, the feedback loop modifies the picture beyond
all recognition.
At a low level, the neural network might be tasked merely to detect
the edges on an image. In that case, the picture becomes painterly, an
effect that will be instantly familiar to anyone who has experience
playing about with photoshop filters:
The pictures are stunning, but they’re more than just for show.
Neural networks are a common feature of machine learning: rather than
explicitly programme a computer so that it knows how to recognise an
image, the company feeds it images and lets it piece together the key
features itself.
But that can result in software that is rather opaque. It’s difficult
to know what features the software is examining, and which it has
overlooked. Fist tap John Kurman.
