|
| |
| M.T. Rosenstein and P.R. Cohen. Concepts from time series. In Proceedings of the Fifteenth National Conference on Artificial Intelligence, 739-745, 1998. | |
| Abstract: This paper describes a way of extracting concepts from streams of sensor readings. In particular, we demonstrate 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 membership and predictive inference. | |
| Download: pdf (270KB), ps.gz (181KB) | |
| See also: | |
|
Continuous categories for a mobile robot | |
|
Symbol grounding with delay coordinates | |
|
Action representation, prediction and
concepts |
|
|
updated 05-Sep-2000 mtr@cs.umass.edu |