Darpa’s Self-Learning Software Knows Who You Are


Software systems could one day analyze everything from blurry war-zone footage to the subtle sarcasm in a written paragraph, thanks to two unassuming scientists who are inspired by biology to make revolutionary strides in intelligent computing.

Yann LeCun and Rob Fergus, both computer science professors at New York University, are the brains behind “Deep Learning,” a program sponsored by Darpa, the Pentagon’s blue-sky research agency. The idea, ultimately, is to develop code that can teach itself to spot objects in a picture, actions in a video, or voices in a crowd. LeCun and Fergus have $2 million and four years to make it happen.

Existing software programs rely heavily on human assistance to identify objects. A user extracts key feature sets, like edge statistics (how many edges an object has, and where they are) and then feeds the data into a running algorithm, which uses the feature sets to recognize the visual input.

“People spend huge amounts of time building these feature sets, figuring out which are better or more accurate, and then refining them,” LeCun told Danger Room. “The question we’re asking is whether we can create computers that automatically learn feature sets from data. The brain can do it, so why not machines?”

The computer systems will be inspired by biology, but not modeled after it. That’s because researchers still aren’t entirely sure how animals are able to turn inputs — an object, a movement, a sound — into usable information. Ten years ago, a study at MIT helped answer the question. Researchers rewired ferret brains, so that the optical nerve fed into the auditory cortex, and vice versa. But the ferrets still saw and heard normally, leading the team to conclude that brain function depends on the signal — not the area.

Brains also display plenty of abstraction when it comes to identifying specific inputs: LeCun was inspired to create his algorithmic layering approach, called “a convolutional network,” by the 1960s research of David Hubel and Torstein Weisel. The two used cats to demonstrate how the brain’s visual cortex relies on abstractions to create complex representations of a given visual input.

In other words, LeCun said, “There’s some sort of learning algorithm within the brain. We just don’t know what it is.”
img_1779

But the algorithmic talents of the mind, along with its ability to identify visual data by abstraction, will be the key components of the NYU team’s new system. Right now, an algorithm recognizes objects in one of two ways. In one, it is shown some representative examples of what, say, a horse looks like. Then the code tries to match any new creature to the ur-stallion. (That’s called “supervised” learning.) In the other way, the software is shown lots and lots of horses, and it builds its own model of what a horse is supposed to resemble. (That’s “unsupervised” learning.)

What LeCun and Fergus are trying to do is make code that can get it right on a first, unsupervised example — using layer after layer of code to abstract the essential attributes of an object. This first step is to turn an image into numbers: For a 100 x 100 pixel image, the software produces a grid of 10,000 numbers; 9 x 9 “masks” are then applied to that grid, to uncover attributes of the image. The first feature spotted is an object’s edge. (The human brain makes a similar initial pass.)
Several more “masks” follow. The final output? A series of 256 numbers that identifies the input.

The two are only six weeks into the project, but they’ve already got demos up and running.

The Deep Learning algorithm and I had never met, but with a quick shot by a small webcam on LeCun’s laptop, the layers of code captured my features and could immediately distinguish me from other objects and people in LeCun’s office. The same thing happens when LeCun introduces the system to two different coffee mugs — it takes mere seconds for the computer to acquaint itself with each, then distinguish one from the other.

And this is only the beginning. Darpa also wants a system that can spot activities, like running, jumping or getting out of a car. The final version will operate unsupervised, by being programmed to hold itself accountable for errors — and then auto-correct them at each algorithmic layer.

It should also be able to apply the layered algorithmic technique to text. Right now, computer systems can parse sentences to categorize them as positive or negative, based on how often different words appear in the text. By applying layers of analysis, the Deep Learning machine will — LeCun and Fergus hope — spot sarcasm and irony too.

“Ideally, what we’ll come away with is a ‘generic learning box’ that can identify every data cue,” Fergus tells Danger Room.

Photo: Katie Drummond
See Also:

Source: http://www.wired.com/
By Katie Drummond"">Katie Drummond, May 21, 2010

Views: 41

Comment

You need to be a member of 12160 Social Network to add comments!

Join 12160 Social Network

"Destroying the New World Order"

TOP CONTENT THIS WEEK

THANK YOU FOR SUPPORTING THE SITE!

mobile page

12160.info/m

12160 Administrators

 

Latest Activity

Doc Vega posted a blog post

Donald Trump Gives an Amazing Speech on Freeing America from the Stranglehold of the Deep State

President Trump gives an amazing speech addressing all major challenges to restoring the…See More
9 hours ago
Doc Vega commented on Doc Vega's blog post What Will happen When Robot Brides Replace Human Marriage?
"Less Prone thanks for your support Buddy! "
10 hours ago
Less Prone favorited tjdavis's video
yesterday
Less Prone posted a photo

Social Engineering 101

That's how it goes.
yesterday
Doc Vega posted a blog post

A Prelude to WW III ? It Seems There We Are Trailblazing Idiocy into More Blood and Destruction!

They're rolling out the 25th Amendment trying to stop Joe Biden from insanely thrusting the US in a…See More
yesterday
Less Prone posted a video

Chris Langan - The Interview THEY Didn't Want You To See - CTMU [Full Version; Timestamps]

DW Description: Chris Langan is known to have the highest IQ in the world, somewhere between 195 and 210. To give you an idea of what this means, the average...
Wednesday
Doc Vega posted a blog post

RFK Jr. Appoinment Rocks the World of the Federal Health Agncies and The Big Pharma Profits!

The Appointment by Trump as Secretary of HHS has sent shockwaves through the federal government…See More
Tuesday
tjdavis posted a video

Somewhere in California.

Tom Waites and Iggy Pop meet in a midnight diner in Jim Jarmusch's 2003 film Coffee and Cigarettes.
Tuesday
cheeki kea commented on cheeki kea's photo
Thumbnail

1 possible 1

"It's possible, but less likely. said the cat."
Monday
cheeki kea posted a photo
Monday
tjdavis posted a blog post
Monday
Tori Kovach commented on cheeki kea's photo
Thumbnail

You are wrong, all of you.

"BECAUSE TARIFFS WILL PUT MONEY IN YOUR POCKETS!"
Monday
Tori Kovach posted photos
Monday
Doc Vega posted a blog post

Whatever Happened?

Whatever Happened?  The unsung heroes will go about their dayRegardless of the welcome they've…See More
Sunday
Doc Vega commented on Doc Vega's blog post A Requiem for the Mass Corruption of the Federal Government
"cheeki kea Nice work! Thank you! "
Sunday
cheeki kea commented on Doc Vega's blog post A Requiem for the Mass Corruption of the Federal Government
"Chin up folks, once the low hanging fruit gets picked off a clearer view will reveal the higher…"
Nov 16
Doc Vega's 4 blog posts were featured
Nov 16
tjdavis's blog post was featured
Nov 16
cheeki kea commented on cheeki kea's blog post Replicon Started in Tokyo October 08, 2024
"Your right LP it's insane for sure and hopefully improbable, keeping an open mind. Checking…"
Nov 16
rlionhearted_3 commented on tjdavis's blog post Bill Gates Deleted Documentary
Nov 16

© 2024   Created by truth.   Powered by

Badges  |  Report an Issue  |  Terms of Service

content and site copyright 12160.info 2007-2019 - all rights reserved. unless otherwise noted