Google’s image recognition software is an incredible feat of engineering. Based on the structure of a biological brain, the ‘artificial neural network’ (ANN) consists of 20–30 stacked layers of artificial ‘neurons’, each neuron talking to the next to decipher what it can ‘see’ in a given image.

Like a human brain, the ANN is ‘trained’ to recognise objects and elements of a picture, with the neurons constantly adjusting and learning until together, they are able to accurately recognise, say, a dog, a banana, a tree.

But the ANN is not yet perfect. In an effort to understand precisely what is happening at each layer of the network, programmers decided to try turning the network upside down: instead of the ANN simply recognizing elements of an image, would it be able to recreate the image?

The results were surprising – often beautiful, and sometimes pretty creepy!

You see, while our human brain can look at clouds in the sky and sometimes imagine that they look like a bird, or a heart, or a face, we know that clouds are clouds. But the ANN doesn’t know that, yet.

When presented with a picture of clouds and asked to recreate it, this happened:

Within the clouds, the ANN saw elements it recognised of birds and buildings, so that’s what it drew!

The software is biased to visualizing pictures of animals, plants and buildings, since images of these things have been used to help train the software in the first place. Nevertheless, some of the effects produced are quite amazing. Here are a few more examples.

See this article for more amazing images! http://www.cnet.com/news/the-surreal-dreams-of-googles-image-recognition-software/.

About the Author:

Although her primary niche is in scientific writing and editing, freelance writer Lisa Martin is also a creative type with an eye for design. She regularly works alongside graphic designers and as such has a keen interest in the development of logos and branding.