Title :
Achievable rates for pattern recognition: binary and Gaussian cases
Author :
Westover, M. Brandon ; O´Sullivan, Joseph A.
Author_Institution :
Dept. of Phys., Washington Univ., St. Louis, MO
Abstract :
Recently we presented information-theoretic bounds for the achievable rates of pattern recognition systems operating under data compression constraints. In this paper we improve on our previous inner bound, and report progress toward finding formulas for the achievable rate region boundaries in the special cases where the pattern data is either binary or Gaussian
Keywords :
Gaussian processes; data compression; information theory; pattern recognition; Gaussian data; binary data; data compression constraints; information-theoretic; pattern recognition; Computer aided software engineering; Data compression; Data engineering; Information theory; Memoryless systems; Pattern recognition; Physics; Probability distribution; System testing; Systems engineering and theory;
Conference_Titel :
Information Theory, 2005. ISIT 2005. Proceedings. International Symposium on
Conference_Location :
Adelaide, SA
Print_ISBN :
0-7803-9151-9
DOI :
10.1109/ISIT.2005.1523286
