Self-Taught: Software That Learns By Doing

Machine-learning techniques to create self-improving software are hitting the mainstream.

By Gary Anthes

February 6, 2006 12:00 PM ET

Computerworld - Attempts to create self-improving software date to the 1960s. But "machine learning," as it's often called, has remained mostly the province of academic researchers, with only a few niche applications in the commercial world, such as speech recognition and credit card fraud detection. Now, researchers say, better algorithms, more powerful computers and a few clever tricks will move it further into the mainstream.


Stanford professor Sebastian Thrun with "Stanley," the car that used machine-learning techniques to drive itself 132 miles across the desert.

And as the technology grows, so does the need for it. "In the past, someone would look at a problem, write some code, test it, improve it by hand, test it again and so on," says Sebastian Thrun, a computer science professor at Stanford University and the director of the Stanford Artificial Intelligence Laboratory. "The problem is, software is becoming larger and larger and less and less manageable. So there's a trend to make software that can adapt itself. This is a really big item for the future."
Thrun used several new machine-learning techniques in software that literally drove an autonomous car 132 miles across the desert to win a $2 million prize for Stanford in a recent contest put on by the Defense Advanced Research Projects Agency. The car learned road-surface characteristics as it went. And machine-learning techniques gave his team a productivity boost as well, Thrun says. "I could develop code in a day that would have taken me half a month to develop by hand," he says.
Computer scientist Tom Mitchell, director of the Center for Automated Learning and Discovery at Carnegie Mellon University, says machine learning is useful for the kinds of tasks that humans do easily -- speech and image recognition, for example -- but that they have trouble explaining explicitly in software rules. In machine-learning applications, software is "trained" on test cases devised and labeled by humans, scored so it knows what it got right and wrong, and then sent out to solve real-world cases.
Mitchell is testing the concept of having two classes of learning algorithms in essence train each other, so that together they can do better than either would alone. For example, one search algorithm classifies a Web page by considering the words on it. A second one looks at the words on the hyperlinks that point to the page. The two share clues about a page and express their confidence in their assessments.
Mitchell's experiments have shown that such "co-training" can reduce errors by more than a factor

Recommend Digg Twitter ShareThis

Email Print Send Feedback Reprints

Additional Resources

POLL RESULTS

Leading IT Pros Weigh In on Top IT Issues

Accelerate your knowledge of the IT world you inhabit by viewing the results of a series of polls taken by your IT peers. These polls of 100+ IT professionals each are available for full viewing. They cover key topics such as virtualization, processor performance, green IT, cloud computing and many others. Be a part of the buzz.

WHITE PAPER

For Best Results, Think Beyond the Box

Technology is complex. Keeping it running productively shouldn't be. To that end, you want to minimize the number of solutions needed in-house to simplify operations, maintenance, and support. Kodak offers a best-practices model. One company provides support for both scanner and software, for fast problem resolution without vendor finger-pointing. Download now!

WHITE PAPER

Accelerating the Path to Demand Intelligence with a Demand Signal Repository

Utilizing demand intelligence improves the precision of pricing, product assortments, channel/store placement, and promotion, which are all essential for sustainable revenue management performance. Learn more, download this free whitepaper today.

White Papers & Webcasts

Differentiating With Technical Support: JBoss Customer Support Study
JBoss' expert technical support services is clearly acknowledged by its client base. The comprehensive nature by which their service is unsurpassed. Every category...

Managing And Protecting Your Ever Increasing Mobile Assets
(Source: Absolute Software) Your users are becoming more mobile each day. This is great for productivity - yet challenging for IT control. Natalie...

The JBoss SOA Assessment Tool: Spend Less, Do More
SOA does not have to be overly complex or expensive. The JBoss SOA Assessment Tool can help you chart a course to a...

IDC Webcast: Linux Adoption in a Global Recession
Join Al Gillen from IDC and Michael Applebaum from Novell in this on-demand webcast to see how Linux has emerged as an even...

The CIO's New Guide to Design of Global IT Infrastructure
Is it possible to eliminate the impact of distance? This paper explores the 5 key principles successful CIOs are using to redesign IT...

Novell Opens PR Video
Is the Linux desktop for me? Customers are looking for ways to be more flexible and save money. Using Linux offers a great...

IBM Lotus Notes Performance Brief
This is a Performance Brief that illustrates how Riverbed Steelhead appliances accelerate Lotus Notes R7....

2 Minutes to IT workload automation
Take just 2 minutes to watch this short CONTROL-M flash video. Well show you how BMC CONTROL-M can put money back into your...

Business Value of Performance IDC Whitepaper
Are you looking for a comprehensive solution that addresses insufficient or congested bandwidth, impaired application performance, slow remote backup and replication or obstacles...

Security Configuration Management
In this web video, follow along with Jim Hansen, Senior Product Manager with Big Fix, as he explains why Security Configuration Management is...

All White Papers | All Webcasts