What Do a Robot's Dreams Look Like? Google Found Out

They may look odd, but it’s all part of Google’s plan to solve a huge issue in machine learning: recognizing objects in images.

Google's artificial neural networks produce some trippy images thanks to its Deep Dream program (photo credit: Michael Tyka/Google)
Google's artificial neural networks produce some trippy images thanks to its Deep Dream program (photo credit: Michael Tyka/Google)

When Google asked its neural network to dream, the machine begin to generating some pretty wild images. They may look odd, but it’s all part of Google’s plan to solve a huge issue in machine learning: recognizing objects in images.

To be clear, Google’s software engineers didn’t ask a computer to dream, but they did ask its neural network to alter the images based on an original photo they fed into it, by applying layers. This was all part of their Deep Dream program.
 
The purpose was to make it better at finding patterns, which computers are none too good at. So, engineers started by “teaching” the neural network to recognize certain objects by giving it 1.2 million images, complete with object classifications the computer could understand.

These classifications allowed Google’s AI to learn to detect the different qualities of certain objects in an image, like a dog and a fork. But Google’s engineers wanted to go one step further, which is where Deep Dream comes in, which allowed the neural network to add those hallucinogenic qualities to images




Google wanted to make its neural network better at detection to the point where it could pick out other objects in an image that may not contain that object (think of it as seeing the outline of a dog in the clouds). Deep Dream gave the computer the ability to change the rules and parameters of the images, which in turn allowed Google’s AI to recognize objects the images didn’t necessarily contain. So, an image might contain an image of a foot, but when it examined a few pixels of that image, it may have seen the outline of what looked like a dog’s nose.

So, when researchers began to ask its neural network to tell them what other objects they might be able to see in an image of a mountain, tree, or plant, it came up with these interpretations:


(Photo Credit: Michael Tyka/Google)

“The techniques presented here help us understand and visualize how neural networks are able to carry out difficult classification tasks, improve network architecture, and check what the network has learned during training,” software engineers Alexander Mordvintsev and Christopher Olah, and intern Mike Tyka wrote in a post about Deep Dream. “It also makes us wonder whether neural networks could become a tool for artists—a new way to remix visual concepts—or perhaps even shed a little light on the roots of the creative process in general.”

Just for fun, Google has opened up the tool to the public and you can generate your own Deep Dream art here: deepdreamgenerator.com

the-future-of-machine-learning


Live on Monday: Does the US need one billion people?

What would happen if you tripled the US population? Join Matthew Yglesias and Charles Duhigg at 1pm ET on Monday, September 28.

‘Time is elastic’: Why time passes faster atop a mountain than at sea level

The idea of 'absolute time' is an illusion. Physics and subjective experience reveal why.

ESA
Surprising Science
  • Since Einstein posited his theory of general relativity, we've understood that gravity has the power to warp space and time.
  • This "time dilation" effect occurs even at small levels.
  • Outside of physics, we experience distortions in how we perceive time — sometimes to a startling extent.
Keep reading Show less

Learn innovation with 3-star Michelin chef Dominique Crenn

Dominique Crenn, the only female chef in America with three Michelin stars, joins Big Think Live.

Big Think LIVE

Having been exposed to mavericks in the French culinary world at a young age, three-star Michelin chef Dominique Crenn made it her mission to cook in a way that is not only delicious and elegant, but also expressive, memorable, and true to her experience.

Keep reading Show less

Universe works like a cosmological neural network, argues new paper

Controversial physics theory says reality around us behaves like a computer neural network.

Synapses in space.

Credit: sakkmesterke
Surprising Science
  • Physicist proposes that the universe behaves like an artificial neural network.
  • The scientist's new paper seeks to reconcile classical physics and quantum mechanics.
  • The theory claims that natural selection produces both atoms and "observers".
Keep reading Show less

We studied what happens when guys add their cats to their dating app profiles

43% of people think they can get a sense of someone's personality by their picture.

Photo by Luigi Pozzoli on Unsplash
Sex & Relationships

If you've used a dating app, you'll know the importance of choosing good profile pics.

Keep reading Show less
Coronavirus

Quarantine rule breakers in 17th-century Italy partied all night – and some clergy condemned the feasting

17th-century outbreaks of plague in Italy reveal both tensions between religious and public health authorities.

Scroll down to load more…
Quantcast