Google's "Unsupervised" Self-Learning Neural Network Searches For Cat Pics
June 26, 2012 2:30 PM
(Source: Pop Kitten)
Magic happens at Google Inc.'s (
) X Laboratory, a secret research and development center located at an unknown location in the Bay Area of Northern California. Some projects previously disclosed have been the
augmented reality "Google Goggles"
. Google X is even rumored to be working on
a space elevator
I. AI Neural Net Loves Cats
But one of the most fascinating -- and perhaps frightening -- Google X accomplishment has been its creation of one of the world's largest self-learning
"unsupervised" neural networks
. Consisting of 16,000 computer processors, the array is capable of complex task that are considered impossible using traditional algorithms. One such task is finding cute cats on the internet.
As a test of the nascent cognizant system,
Electrical Engineering Professor
Andrew Y. Ng
and Google fellow Jeff Dean fed the machine 10 million thumbnails of YouTube videos. Without being told exactly what to "look for", the network began to hierarchically arrange data, removing duplicate similar features and group certain images together.
One example was the cat. Thanks to the wealth of cat videos on YouTube, the cyber-brain eventually came to a single dream-like image representing the network's knowledge of what a cat looks like. The network was able to then able to recognize its favorite thing -- cat videos, no matter what subtle variations merry YouTubers come up with to their feline's appearance.
The "cat neuron" holds the learned appearance of what a cat looks like.
[Image Source: Jim Wilson/The New York Times]
The significant part, say researchers, is that the network wasn't told what to look for.
in an interview in
New York Times
, "We never told it during the training, ‘This is a cat.' It basically invented the concept of a cat. We probably have other ones that are side views of cats."
II. Future Systems May Match or Beat Human Brain
Google researchers believe this capability is due to the fact that the network operates similarly to the visual cortex in the human brain. The visual cortex is thought to contain so-called "grandmother neurons", which store key images, such as your love ones' faces. The system developed an idea of what a human face looks like, though it lacked the specificity of known faces stored in the human visual cortex.
The system taught itself what a human looks like. [Image Source: Google]
Dr. Ng describes, "A loose and frankly awful analogy is that our numerical parameters correspond to synapses [in the human brain]."
He says that despite that the network learned what a cat looks like and many basic human features, that it still had far less connections ("synapses") than a human brain. In short, mankind is still winning versus his digital counterpart. Writes the team, "It is worth noting that our network is still tiny compared to the human visual cortex, which is a million times larger in terms of the number of neurons and synapses."
David A. Bader
, executive director of high-performance computing at the
College of Computing, though, says that the team's findings indicate that mankind's era of superiority will be short-lived. He comments, "The scale of modeling the full human visual cortex may be within reach before the end of the decade."
In a difficult test of recognizing 20,000 images, the system performed better than any machine to date, post-learning. The final accuracy was 15.8 percent, 70 percent better than the previous record-holder.
The work was
29th International Conference on Machine Learning
in Edinburgh, Scotland.
The project is now headed out of the top-secret lab and into Google's server farms. Applications that it may be used in include improving results in Google's image search and adaptive speech recognition for Android mobile devices.
But Professor Ng has his sights set on a far more ambitious goal -- a machine that is capable of fully learning, developing into a
fully sentient digital system
. To get there he'll need to wait for the never-ending process of hardware improvements to reach a bit further and he'll also have to work on the fundamental algorithms.
The Google X system is close, but not quite there. He states, "It’d be fantastic if it turns out that all we need to do is take current algorithms and run them bigger, but my gut feeling is that we still don’t quite have the right algorithm yet."
The New York Times
"Can anyone tell me what MobileMe is supposed to do?... So why the f*** doesn't it do that?" -- Steve Jobs
Report: Wearable Android Google Goggles Will Debut in 2012 for Under $600
February 22, 2012, 11:30 AM
IBM Researchers Develop Neurosynaptic Chips for Cognitive Computing
August 18, 2011, 11:44 AM
Google Developing Self-Piloted Cars
October 11, 2010, 7:22 AM
Leading Neuroscientists Blasts DARPA Cat-Brain Project Calling it a "Scam"
November 24, 2009, 5:18 AM
Carefully Timed Rhythmic Jerks Could Drive Space Elevator
January 6, 2009, 8:15 AM
Netflix took a decision to invest in original content
January 19, 2017, 7:00 AM
Amazon Airborne Fulfillment Center – Your Merchandise Drop-Shipped from the Clouds
December 29, 2016, 5:00 AM
Amazon is experimenting with a new kind of grocery stores, Amazon Go
December 8, 2016, 5:00 AM
Google has developed Deep Learning Algorithm to detect Diabetic Eye Disease
December 4, 2016, 5:00 AM
Google plans ultra-fast wireless Internet for Research Triangle Park, N.C.
August 12, 2016, 6:30 AM
Twitter Senior VP: "Diversity is Important, But We Can’t Lower the Bar"
November 9, 2015, 9:59 AM
Most Popular Articles
Super Hi- Vision Will Amaze the World
January 16, 2017, 9:53 AM
Comparison: Xiaomi Mi Mix Vs. HTC U Ultra
January 14, 2017, 12:10 AM
A Few Technology Trends, Highlight’s of 2017
January 14, 2017, 12:31 AM
Gionee Marathon M5 Plus – China’s Flagship Smartphone
January 15, 2017, 2:02 AM
Samsung Chromebook Plus – Coming in February 2017
January 17, 2017, 12:01 AM
Latest Blog Posts
Jan 20, 2017, 7:00 AM
News of the World
Jan 19, 2017, 7:00 AM
News of the Day Wednesday 1/18/2017
Jan 18, 2017, 12:01 AM
Jan 17, 2017, 12:16 AM
News of the Day
Jan 16, 2017, 12:10 PM
News and Technology Advancement
Jan 16, 2017, 7:58 AM
Jan 15, 2017, 12:32 AM
Here is Some News
Jan 14, 2017, 12:39 AM
News: Improved and New products
Jan 13, 2017, 12:01 AM
News around the world
Jan 12, 2017, 12:01 AM
Rumors and Announcements
Jan 11, 2017, 12:01 AM
This year CES and ridiculous gadgets
Jan 10, 2017, 12:01 AM
Nokia Android phone spurns the west.
Jan 9, 2017, 12:08 AM
New at CES 2017 - Changhong 8K Super Slim TV 65ZHQ3R
Jan 8, 2017, 1:07 AM
Debuted at CES 2017 - Vuzix Blade 3000 Smart Sunglasses
Jan 8, 2017, 12:39 AM
Some news of Day
Jan 7, 2017, 12:01 AM
News 2017 CES
Jan 6, 2017, 12:01 AM
Here is the Latest News in Tech
Jan 5, 2017, 1:47 AM
AI Beats World’s Best at Chinese board game “Go”
Jan 4, 2017, 11:21 AM
Las Vegas 2017 CES
Jan 3, 2017, 12:01 AM
More Blog Posts
Copyright 2017 DailyTech LLC. -
Terms, Conditions & Privacy Information