HPCwire: Supercomputer Learns How to Recognize Cats

Since 1986 - Covering the Fastest Computers
in the World and the People Who Run Them

Translation Disclaimer

Subscribe | Sign In

Visit additional Tabor Communication Publications

Leading HPC
Solution Providers

June 28, 2012

Supercomputer Learns How to Recognize Cats

Robert Gelber

Search giant Google along with researchers from Stanford University have made an interesting discovery based on an X labs project. After being fed 10 million images from YouTube, a 16,000-core cluster learned how to recognize various objects, including cats. Earlier this week, the New York Times detailed the program, explaining its methods and potential use cases.

The project began a few years ago when Google researchers planned to make a human brain simulation. The compute cluster acted as the brain’s neural network, tasked with learning on its own and using the Internet as a source of information. After processing millions of unlabeled YouTube thumbnails, the system taught itself how to recognize a cat. While the video website is known for its comprehensive collection of user submitted feline antics, project researchers were focused on the simulation’s ability to learn objects without human input.

A 1,000-node cluster was the basis for the neural network, representing more than 1 billion connections. The unlabeled images were collected randomly and processed by machine-learning algorithms. Similar to IBM’s Watson, the technology relies on “deep learning” techniques, using previous outcomes to inform future decisions. Machine learning has also become integral in other applications, including speech recognition.

The researchers removed all identifying labels from the images because they wanted to see if the network was able to create the concept of an object. Dr. Jeff Dean of Stanford University explained how the project differs from other recognition technologies. “We never told it during the training, ‘This is a cat,’ ” he said “It basically invented the concept of a cat. We probably have other ones that are side views of cats.”

As a result, the software generated a vague image of a cat on its own. The simulation has also introduced possible evidence of “grandmother neurons”, which some believe are specialized cells, trained to recognize an individual face or concept.

It’s not all about cats, of course. The system was also able to identify human faces and bodies to some degree. Compared to previous attempts to identify unlabeled images, the simulation fared much better at learning and recognition. According to the researchers’ findings, they were able to deliver 15.8 percent accuracy in recognizing 20,000 object categories. They claim that’s 70 percent better than what had been achieved previously.

According to David Bader, executive director of high-performance computing at the Georgia Tech College of Computing, the simulation represents an improvement of “an order of magnitude over previous efforts.” He believes this work could lead to a complete model of the human visual cortex before the end of the decade.

Full story at The New York Times

Share Options

Subscribe

Subscribe to HPCwire

Discussion

There are 0 discussion items posted.

Join the Discussion

Become a Registered User Today!

Registered Users Log in join the Discussion

RSS Feeds

Feeds by Topic

Feeds by Industry

Feeds by Content Type

Subscribe to All Content

All

June 29, 2012

Building America Reinvesting Tax Credits In HPC Center

June 28, 2012

June 27, 2012

June 26, 2012

June 25, 2012

June 21, 2012

June 20, 2012

June 19, 2012

Feature Articles

The Uber-Cloud Experiment

Even with its promise of easy access to pay-per-use computing, HPC-as-a-Service as a delivery model has yet to be widely embraced by high performance computing users. In this article, authors Wolfgang Gentzsch and Burak Yenier describe an HPC service experiment that brings together industry users, resource providers, software providers, and HPC experts, which they believe will help pave the way for wider adoption.
Read more...

Lawrence Livermore, IBM Offer Petascale Supercomputer to Industry

One by one, US government HPC labs are getting into the industry partnership business. The latest is Lawrence Livermore National Laboratory (LLNL), who this week announced it was teaming with IBM to form "Deep Computing Solutions," a collaboration that is being folded into LLNL’s new High Performance Computing Innovation Center,
Read more...

An HPC Programming Model for the Exascale Age

As the supercomputing faithful prepare for exascale computing, there is a great deal of talk about moving beyond the two-decades-old MPI programming model . The HPC programmers of tomorrow are going to have to write codes that are able to deal with systems hundreds of times larger than the top supercomputers of today, and the general feeling is that MPI, by itself, will not make that transition gracefully. One of the alternatives being offered is a PGAS model known as GASPI...
Read more...

Read more HPCwire features...

Tackling the Data Deluge: File Systems and Storage Technologies

06/25/2012 | NetApp | A single hour of data collection can result in 7+ million files from just one camera. Collection opportunities are limited and must be successful every time. As defense and intelligence agencies seek to use the data collected to make mission-critical battlefield decisions, there’s greater emphasis on smart data and imagery collection, capture, storage and analysis to drive real-time intelligence. The data gathered must accurately and systematically be analyzed, integrated and disseminated to those who need it – troops on the ground. This reality leads to an inevitable challenge – warfighters swimming in sensors, drowning in data. With the millions, if not billions, of sensors providing all-seeing reports of the combat environment, managing the overload demands a file system and storage infrastructure that scales and performs while protecting the data collected. Part II of our whitepaper series highlights NetApp’s scalable, modular, and flexible storage solution to handle the demanding requirements of sophisticated ISR environments.