Information measures of individual sequences with application to universal data compression and hypothesis testing

• Restricted to UC San Diego use only

A new notion of empirical informational divergence (relative entropy) between two individual sequences is introduced. A simple universal classification algorithm of individual sequences into a finite number of classes which is based on this empirical divergence, is introduced. It discriminates between classes which are distinguishable by some finite-state classifier, for almost every given training set and almost any test sequence from these classes

• 1992

• Merhav, N
• University of California, San Diego, Dept. of Electrical and Computer Engineering
• Ziv, Jacob

Jacob Ziv, presenter

Recorded May 19, 1992 at the University of California, San Diego

1 video file

Preservation DVD copy (1 videodisc (ca. 89 min.) : sd., col. ; 4 3/4 in.) of original VHS tape item

videodisc

videorecording

Lecture sponsored by the Dept. of Electrical and Computer Engineering, University of California, San Diego

Title on container: A measure of relative entropy between individual sequences with application to universal classification

• Videorecording

• Pattern recognition systems

• video

• English

General related resource

• ECE distinguished lecturer

Under copyright (US)

Use: This work is available from the UC San Diego Library. This digital copy of the work is intended to support research, teaching, and private study.

Constraint(s) on Use: This work is protected by the U.S. Copyright Law (Title 17, U.S.C.). Use of this work beyond that allowed by "fair use" requires written permission of the copyright holder(s). Responsibility for obtaining permissions and any use and distribution of this work rests exclusively with the user and not the UC San Diego Library. Inquiries can be made to the UC San Diego Library program having custody of the work.

Special Collections & Archives, UC San Diego, La Jolla, 92093-0175 (https://lib.ucsd.edu/sca)

2020-10-22