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

When seen through the lens of technology, few resources are truly scarce; they’re mainly inaccessible. 

 

Peter Diamandis

DeepMind AI teaches itself about the world by watching videos

RATE THIS! +48
Posted in Software on 12th Aug, 2017 04:29 PM by Alex Muller

DeepMind has developed an AI that teaches itself to recognise a range of visual and audio concepts just by watching tiny snippets of video. This AI can grasp the concept of lawn mowing or tickling, for example, but it hasn’t been taught the words to describe what it’s hearing or seeing.

 
“We want to build machines that continuously learn about their environment in an autonomous manner,” says Pulkit Agrawal at the University of California, Berkeley. Agrawal, who wasn’t involved with the work, says this project takes us closer to the goal of creating AI that can teach itself by watching and listening to the world around it.
 
Most computer vision algorithms need to be fed lots of labelled images so it can tell different objects apart. Show an algorithm thousands of cat photos labelled “cat” and soon enough it’ll learn to recognise cats even in images it hasn’t seen before.
 
But this way of teaching algorithms – called supervised learning –  isn’t scalable, says Relja Arandjelović who led the project at DeepMind. Instead of relying on human-labelled datasets, his algorithm learns to recognise images and sounds by matching up what it sees with what it hears.
 
Humans are particularly good at this kind of learning , says Paolo Favaro at the University of Bern in Switzerland. “We don’t have somebody following us around and telling us what everything is,” he says.
 
Arandjelović created his algorithm by starting with two networks – one that specialised in recognising images and another that did a similar job with audio. He showed the image recognition network stills taken from short videos while the audio recognition network was trained on 1-second audio clips taken from the same point in each video.
 
A third network compared still images with audio clips to learn which sounds corresponded with which sights in the videos. In all, the system was trained on 60 million still-audio pairs taken from 400,000 videos.
 
The algorithm learned to recognise audio and visual concepts, including crowds, tap dancing and water, without ever seeing a specific label for a single concept. When shown a photo of someone clapping, for example, most of the time it knew which sound was associated with that image.
 
This kind of co-learning approach could be extended to include senses other than sight and hearing, says Agarwal. “Learning visual and touch features simultaneously can, for example, enable the agent to search for objects in the dark and learn about material properties such as friction,” he says.
 
DeepMind will present the study at the International Conference on Computer Vision which takes place in Venice, Italy, in late October.
 
While the AI in the DeepMind project doesn’t interact with the real world, Agarwal says that perfecting self-supervised learning will eventually let us create AI that can operate in the real world and learn from what it sees and hears.
 
But until we reach that point, self-supervised learning might be a good way of training image and audio recognition algorithms without input from vast amounts of human-labelled data. The DeepMind algorithm can correctly categorise an audio clip nearly 80 per cent of the time, making it better at audio-recognition than many algorithms trained on labelled data.
 
Such promising results suggest that similar algorithms might be able to learn something by crunching through huge unlabelled datasets like YouTube’s millions of online videos. “Most of the data in the world is unlabelled and therefore it makes sense to develop systems that can learn from unlabelled data,” Agrawal says.

Tags: DeepMindAIvideosoftwareGoogleAlphabet

Read original article » Back to category

Comments

Author: Guest
Posted: 2017-08-13
+1
AI needs further development for wider applications and learning about the world like humans do would help greatly - The Deep Mind has a good idea, hopefully it will work
1 Replies
Author: Guest
Posted: 2017-08-13
+1
Yes, after videos, it could be learning from the real world .... Reply
Reply


 

Recent headlines

  • Posted in Science on 2017-11-24 09:26:38
    Spacex dedicated tanker versions of BFS for orbital.....read more
    Posted in Hardware on 2017-11-24 09:18:26
    China solar must increase 600% to displace coal, gas and.....read more
    Posted in Business on 2017-11-24 09:14:25
    Oculus: VR Flourishes Despite Predictions of its Death..read more
    Posted in Business on 2017-11-22 23:55:15
    How to Use Technology to Help You Become Debt-Free..read more
    Posted in Medicine on 2017-11-22 23:49:31
    Patients On Medical Cannabis More Likely To Quit Opioids,.....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
    Martian landscapes formed from sand 'levitating' on a little.....read more
    Posted by AlexMuller
    Scientists detect comets outside our solar system..read more
    Posted by AlexMuller
    Advanced artificial limbs mapped in the brain..read more
    Posted by AlexMuller
    Bacteria have a sense of touch..read more
    Posted by AlexMuller
    Recurrent brain cancer: New hope with phase 1 clinical trial.....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