Building architectures for autonomous rational behavior requires the integration of several AI components, such as planning, learning and execution monitoring. In most cases, the ...
Many perceptual models and theories hinge on treating objects as a collection of constituent parts. When applying these approaches to data, a fundamental problem arises: how can w...
We propose a framework for policy generation in continuoustime stochastic domains with concurrent actions and events of uncertain duration. We make no assumptions regarding the co...
We present and empirically analyze a machine-learning approach for detecting intrusions on individual computers. Our Winnowbased algorithm continually monitors user and system beh...
We propose a committee-based active learning method for large vocabulary continuous speech recognition. In this approach, multiple recognizers are prepared beforehand, and the rec...