As statistical machine learning algorithms and techniques continue to mature, many researchers and developers see statistical machine learning not only as a topic of expert study, but also as a tool for software development. Extensive prior work has studied software development, but little prior work has studied software developers applying statistical machine learning. This work presents two studies that provide important new insight into difficulties faced by developers and the need for development tools that better support the application of statistical machine learning.

Although existing work has explored both information extraction and community content creation, most research has focused on these issues in isolation. In contrast, we see the greatest leverage in the synergistic pairing of these methods as two interlocking feedback cycles. We explore the potential synergy promised if these cycles can be made to accelerate each other by exploiting the same edits to advance both learning-based information extraction and community content creation.

Many mobile machine learning applications require collecting and labeling data, and a traditional GUI on a mobile device may not be an appropriate or viable method for this task. We present an alternative approach to mobile labeling of sensor data called VoiceLabel. VoiceLabel consists of two components: (1) a speech-based data collection tool for mobile devices, and (2) a desktop tool for offline segmentation of recorded data and recognition of spoken labels.

Overly complicated directions generated by navigation services increase the cognitive load of the user, which may lead to a dangerous driving environment. We have developed a system, called MyRoute, that reduces route complexity by creating user specific routes based on a priori knowledge of familiar routes and landmarks.

Tele-immersive virtual reality allows users to share the same physical space as virtual objects. As such, it presents a compelling environment for learning physical tasks. By observing the subjects learn Tai Chi in a fully tele-immersive environment, we answer questions such as the following: How well do students learn in a VR? How good a substitute is a virtual teacher for a real teacher? Finally, are there any tangible benefits to the immersion resulting from fully tele-immersive systems?

Nearly all published structure from motion (SFM) algorithms are offline, that is, they require the entire data set for processing. Our algorithm exploits the notion of conditional independence in Rao-Blackwellized particles, allowing us to decouple the complexity of the algorithm from the size of the data set. By doing so, we are able to utilize a particle filter to perform structure from motion as an online algorithm.

When detecting anomalous traffic patterns in web applications, visualization techniques can be used to enable pattern recognition by humans creating synergy with automatic pattern recognition techniques.

As speed increases the amount of sensor information about the terrain decreases. We address the problem of sensor control in the context of this speed-coverage trade off. We provide an algorithm for deciding where the vehicle should look based where its current information about the environment.

Hypernym classification is the task of deciding whether, given two words, one word “is a kind of” the other. We present a classifier that learns the noun hypernym relation based on automatically-discovered lexico-syntactic patterns between a set of provided hyponym/hypernym noun pairs.

LARRI (previously Symphony) integrates wearable computing with speech recognition to provide hands-free assistance for procedural tasks such and repair or maintenance. The system was taken on a field trial on two occasions where it was used by professional aircraft mechanics.