Concepts From Time Series
Michael T. Rosenstein, Paul R. Cohen · 1998
This paper describes a way of extracting concepts from streams of sensor readings. In particular, we demon-strate the value of attractor reconstruction techniques for transforming time series into clusters of points. These clusters, in turn, represent perceptual categories with predictive value to the agent/environment system. We also discuss the relationship between categories and concepts, with particular emphasis on class member-ship and predictive inference.