Social Media Sidebar

Announcement

Please sign up, comment on articles and bring your friends!

Current poll

PlanetTech is asking:

What do you think about our new web site?

Love it, indeed
Really good solution
Same as old one
The old one was better
This is a new option

Quote of the day

Just because something doesn’t do what you planned it to do doesn’t mean it’s useless.

 

Thomas Edison

DeepMind AI can 'imagine' a world based on a picture

RATE THIS! +17
Posted in Software on 16th Jun, 2018 12:15 AM by Alex Muller

DeepMind has developed a neural network that taught itself to ‘imagine’ a scene from different viewpoints, based on just a single image. Given a picture – say, a room, the network can generate a 3D view from a different vantage point, rendering the opposite sides of the objects and altering where shadows fall to maintain the same light source.

 

The system, called the Generative Query Network (GQN), can tease out details from the static images to guess at spatial relationships, including the camera’s position.

 

“Imagine you’re looking at Mt. Everest, and you move a metre – the mountain doesn’t change size, which tells you something about its distance from you,”says Ali Eslami who led the project at Deepmind.

 

“But if you look at a mug, it would change position. That’s similar to how this works,”

 

To train the neural network, he and his team showed it images of a scene from different viewpoints, which it used to predict what something would look like from behind or off to the side. The system also taught itself through context about textures, colours, and lighting. This is in contrast to the current technique of supervised learning, in which the details of a scene are manually labeled and fed to the AI.

 

The AI can also control objects in virtual space, applying its understanding of spatial relationships to a scenario where it moved a robotic arm to pick up a ball. It learns a lot like we do, even if we don’t realise it, says Danilo Rezende at DeepMind, who also worked on the project.

 

By showing the neural network many images in training, it can suss out the characteristics of similar objects and remember them. “If you look inside the model, we can identify groups of artificial neurons, units in the computational graph, that represent the object,” Rezende says.

 

The system moves around these scenes, making predictions about where things should be and what they ought to look like, and adjusting when its predictions are incorrect.

 

It was able to use this ability to work out the layout of a maze after seeing just a few pictures of it taken from different viewpoints.


Tags: AIsoftwaredeep learningartificial intelligence

Read original article » Back to category

Comments



 

Recent headlines

  • Posted in Hardware on 2018-11-13 05:19:55
    NASA certifies SpaceX's Falcon 9 for its most expensive.....read more
    Posted in Software on 2018-11-09 03:19:01
    OpenAI launches reinforcement learning training..read more
    Posted in Science on 2018-11-08 03:58:12
    Plan to find and explore Ocean Worlds and search for life..read more
    Posted in Medicine on 2018-11-06 01:18:21
    Glowing chemical 'could aid brain cancer surgery'..read more
    Posted in Business on 2018-11-06 01:11:11
    Space Force will be more about putting up new space.....read more
Posted in Business on 2013-10-10 01:33
China is working towards a manned lunar mission in about.....read more
Posted in Business on 2013-10-20 07:17
Spacex says China is their main competitor for commercial.....read more
Posted in Software on 2013-10-20 06:43
Pirate Bay Browser Clocks 1,000,000 Downloads..read more
Posted in Medicine on 2013-10-10 02:10
Google reportedly investing hundreds of millions into new.....read more
Posted in Medicine on 2013-10-14 03:13
Endothelial Cells Can Repair and Regenerate Organs,.....read more
Posted in Science on 01.01.2010
Spacex says China is their main competitor for commercial.....read more
Posted in Science on 01.01.2010
Staring at Your Phone Could Be Making You Short Sighted..read more
Posted in Science on 01.01.2010
Oculus Rift virtual reality headset coming to mobile, but.....read more
Posted in Science on 01.01.2010
China is working towards a manned lunar mission in about.....read more
Posted in Science on 01.01.2010
Delivering drugs via nanoparticles to target mitochondria..read more

Recent Blog Posts

  • Posted by AlexMuller
    Even light drinking increases risk of death..read more
    Posted by AlexMuller
    Researchers have discovered how to slow aging..read more
    Posted by AlexMuller
    Human retinas grown in a dish explain how color vision develops..read more
    Posted by AlexMuller
    The smartphone app that can tell you’re depressed before you.....read more
    Posted by AlexMuller
    Neural networks don’t understand what optical illusions are..read more

Login to your Account

Login to your PlanetTech Account here

Username:
Password:
Remember me
or

Create a New Account

You just need username and password

The following errors occured:
Username:
Email:
Password:
Verify password:
Remember me