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
- Path Selection Infographic Path Selection Infographic
- Hyperconvergence Infographic A wide range of observers agree that data centers are now entering an era of "hyperconvergence" that will raise network traffic levels faster...
- Preparing Your Infrastructure for the Hyperconvergence Era From cloud computing and virtualization to mobility and unified communications, an array of innovative technologies is transforming today's data centers.
- Increase IT Performance from the Enterprise to the Cloud with WAN Optimization Massive consolidation and data mobility, enabled by virtualization, have radically altered how we build servers, design applications, and deploy storage for the emerging...
- Live Webcast
Transforming Finance, Procurement and Supply Chain Effectiveness with Cross-Functional Analytics
Date: May 6th, 2014
Time: 1 PM EDT
Attend this Webcast to find out how Oracle's packaged analytic applications enable line-of-business managers to examine all...
- Video Stream Quality Impacts Viewer Behavior This scientific white paper, using statistical data from Amakai's streaming network, analyzes how changes in video quality cause changes in viewer behavior.
- Service-Enabling CICS Applications: Best Practices This informative webcast provides an informed, thorough look into CICS service-enablement options and how they can affect your environment. You'll learn how to... All Applications White Papers | Webcasts