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.
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
Swipe right to make the connections that could change your career.
Swipe right. Match. Meet over coffee or set up a call.
No, we aren't talking about Tinder. Introducing Shapr, a free app that helps people with synergistic professional goals and skill sets easily meet and collaborate.
A NASA astronomer explains how astronauts dispose of their, uh, dark matter.
- When nature calls in micro-gravity, astronauts must answer. Space agencies have developed suction-based toilets – with a camera built in to ensure all the waste is contained before "flushing".
- Yes, there have been floaters in space. The early days of space exploration were a learning curve!
- Amazingly, you don't need gravity to digest food. Peristalsis, the process by which your throat and intestines squeeze themselves, actually moves food and water through your digestive system without gravity at all.
She met mere mortals with and without the Vatican's approval.
- For centuries, the Virgin Mary has appeared to the faithful, requesting devotion and promising comfort.
- These maps show the geography of Marian apparitions – the handful approved by the Vatican, and many others.
- Historically, Europe is where most apparitions have been reported, but the U.S. is pretty fertile ground too.
A growing body of research shows promising signs that the keto diet might be able to improve mental health.
- The keto diet is known to be an effective tool for weight loss, however its effects on mental health remain largely unclear.
- Recent studies suggests that the keto diet might be an effective tool for treating depression, and clearing up so-called "brain fog," though scientists caution more research is necessary before it can be recommended as a treatment.
- Any experiments with the keto diet are best done in conjunction with a doctor, considering some people face problems when transitioning to the low-carb diet.
SMARTER FASTER trademarks owned by The Big Think, Inc. All rights reserved.