Tools for detecting dependencies in AI systems

We present a methodology for learning complex dependencies in data based on streams of categorical, time series data. The streams representation is applicable in a variety of situations: a program's execution trace may be thought of as a stream. The various monitor readings of an intensive care unit may be thought of as concurrent streams. Our learning methodology, called dependency detection, examines a stream or multiple streams to characterize recurring structure with a set of dependency rules. These dependency rules are useful not only as a description of how the data is structured, but as a means for predicting future stream states from those of the present. Further, we describe a set of tools for program analysis that use dependency detection. To appear in Proceedings of the Seventh International IEEE Conference on Tools with Arti cial Intelligence.