Google has revealed what its most advanced artificial systems dream of

The firm has revealed a stunning set of images to help explain how its systems learn over time.

It shows how the system learns and what happens when it gets things wrong.

'Artificial Neural Networks have spurred remarkable recent progress in image classification and speech recognition,' wrote Alexander Mordvintsev, , Christopher Olah and Mike Tyka of Google's AI team.
'But even though these are very useful tools based on well-known mathematical methods, we actually understand surprisingly little of why certain models work and others don't.'
Google trains an artificial neural network by showing it millions of training examples and gradually adjusting the network parameters until it gives the classifications the team want.
The team has even given the images a name - Inceptionism.
The network typically consists of 10-30 stacked layers of artificial neurons.
Each image is fed into the input layer, which then talks to the next layer, until eventually the 'output' layer is reached.
The network's 'answer' comes from this final output layer.
In doing this, the software builds up a idea of what it thinks an object looked like.

If a cloud looks a little bit like a bird, the network will make it look more like a bird.
This in turn will make the network recognize the bird even more strongly on the next pass and so forth, until a highly detailed bird appears, seemingly out of nowhere.
'The results are intriguing—even a relatively simple neural network can be used to over-interpret an image, just like as children we enjoyed watching clouds and interpreting the random shapes.
'This network was trained mostly on images of animals, so naturally it tends to interpret shapes as animals.
'But because the data is stored at such a high abstraction, the results are an interesting remix of these learned features.'

Spoiler

to

I'm ready for AIs, the best thing to happen to humanity