THESE ARE WHAT THE GOOGLE
ARTIFICIAL INTELLIGENCE’S DREAMS LOOK LIKE.
 |
Google's artificial neural
network has some explaining to do.
|
Google's servers drive the
much of the world's data, and apparently, they dream as well, according to a
Google blog post by two Google software engineers and an intern.
Google's artificial neural
network has some explaining to do.
Google’s artificial neural
networks (ANNs) are stacked layers of artificial neurons (run on computers)
used to process Google Images. To understand how computers dream, we first need
to understand how they learn. In basic terms, Google's programmers teach an ANN
what a fork is by showing it millions of pictures of forks, and designating that
each one is what a fork looks like. Each of network's 10-30 layers extracts
progressively more complex information from the picture, from edges to shapes
to finally the idea of a fork.
Eventually, the neural network understands a fork has a handle and two to four tines, and if there are any errors, the team corrects what the computer is misreading and tries again.
The Google team realized that the same process used to discern images could be used to generate images as well. The logic holds: if you know what a fork looks like, you can ostensibly draw a fork.
 |
This is what Google's
neural network thinks animals and objects look like.
|
This showed that even when
shown millions of photos, the computer couldn’t come up with a perfect
Plutonian form of an object. For instance, when asked to create a dumbbell, the
computer depicted long, stringy arm-things stretching from the dumbbell shapes.
Arms were often found in pictures of dumbbells, so the computer thought that
sometimes dumbbells had arms.
This helped refine the
company’s image processing capabilities, but the Google team took it further.
Google used the ANN to amplify patterns it saw in pictures. Each artificial
neural layer works on a different level of abstraction, meaning some picked up
edges based on tiny levels of contrast, while others found shapes and colors.
They ran this process to accentuate color and form, and then by told the
network to go buck wild, and keep accentuating anything it recognizes. So if a
cloud looks similar to a bird, the network would keep applying its idea of a
bird in small iterations over and over again.
Arms were often found in
pictures of dumbbells, so the computer thought that sometimes dumbbells had arms.
Oddly enough, the Google
team found patterns. Stone and trees often became buildings. Leaves often
became birds and insects.
 |
Google's artificial neural
network often found similar patterns in images of rocks or trees.
|
Researchers then set the
picture the network produced as the new picture to process, creating an
iterative process with a small zoom each time, and soon the network began to
create a “endless stream of new impressions.” When started with white noise,
the network would produce images purely of its own design. They call these
images the neural network's "dreams," completely original
representations of a computer's mind, derived from real world objects.
 |
The produce of an
artificial neural network being asked to amplify and pull patterns out of white
noise.
|
 |
The produce of an
artificial neural network being asked to amplify and pull patterns out of white
noise.
|
Google continues to use
these techniques to find out what their artificial neural networks are
learning, and even ponders if it could shed light on the “roots of the creative
process in general.”
