Self-Taught: Software That Learns By Doing
Machine-learning techniques to create self-improving software are hitting the mainstream.
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.
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 of two. The breakthrough, he
- CIOs Deliver Productivity Breakthroughs with Intelligent Digital Signage Retailers have long recognized the influence that digital signage provides over a shopper's point-of-purchase decision making process.
- 2014 Gartner Magic Quadrant Report For the 7th year in a row, Riverbed is in the "Leaders" Quadrant of the 2014 Magic Quadrant for WAN Optimization Controllers. In...
- Improving Business Value of WAN Optimization Want to achieve faster ROI with WAN optimization? Read the latest IDC report and discover how you can cut IT costs without compromising...
- IDC ROI Infographic Trends such as evolving communication patterns, connection types, applications and bandwidth can have an impact on enterprise organizations. Learn how IT organizations can...
- Transform Your IT Service Management Watch this webinar, to learn how EasyVista can increase IT productivity & efficiency and deliver streamlined & integrated IT Service & Asset Mgmt.
- Top 4 Digital Signage Fails Join RMG Networks for a look at four of the most common reasons digital signage fails in corporate businesses. Learn about strategies to... All Applications White Papers | Webcasts