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


‘Designer baby’ book trilogy explores the moral dilemmas humans may soon create

How would the ability to genetically customize children change society? Sci-fi author Eugene Clark explores the future on our horizon in Volume I of the "Genetic Pressure" series.

Surprising Science
  • A new sci-fi book series called "Genetic Pressure" explores the scientific and moral implications of a world with a burgeoning designer baby industry.
  • It's currently illegal to implant genetically edited human embryos in most nations, but designer babies may someday become widespread.
  • While gene-editing technology could help humans eliminate genetic diseases, some in the scientific community fear it may also usher in a new era of eugenics.
Keep reading Show less

Designer uses AI to bring 54 Roman emperors to life

It's hard to stop looking back and forth between these faces and the busts they came from.

Meet Emperors Augustus, left, and Maximinus Thrax, right

Credit: Daniel Voshart
Technology & Innovation
  • A quarantine project gone wild produces the possibly realistic faces of ancient Roman rulers.
  • A designer worked with a machine learning app to produce the images.
  • It's impossible to know if they're accurate, but they sure look plausible.
Keep reading Show less

Ten “keys to reality” from a Nobel-winning physicist

To understand ourselves and our place in the universe, "we should have humility but also self-respect," Frank Wilczek writes in a new book.

Photo by Andy HYD on Unsplash
Surprising Science
In the spring of 1970, colleges across the country erupted with student protests in response to the Vietnam War and the National Guard's shooting of student demonstrators at Kent State University.
Keep reading Show less

This is your brain on political arguments

Debating is cognitively taxing but also important for the health of a democracy—provided it's face-to-face.

Antifa and counter protestors to a far-right rally argue during the Unite the Right 2 Rally in Washington, DC, on August 12, 2018.

Credit: Zach Gibson/AFP via Getty Images
Mind & Brain
  • New research at Yale identifies the brain regions that are affected when you're in disagreeable conversations.
  • Talking with someone you agree with harmonizes brain regions and is less energetically taxing.
  • The research involves face-to-face dialogues, not conversations on social media.
Keep reading Show less
Surprising Science

2020 ties for hottest year on record, says NASA and NOAA

In a joint briefing at the 101st American Meteorological Society Annual Meeting, NASA and NOAA revealed 2020's scorching climate data.

Scroll down to load more…
Quantcast