Learning classifier tables for autonomic systems on chip

J. Zeppenfeld, A. Bouajila, W. Stechele, A. Herkersdorf

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

17 Scopus citations

Abstract

This paper introduces a new hardware-based machine learning building block - called Learning Classifier Table (LCT) - for the run-time reliability, performance and power optimization of future generations of Systems-on-Chip. LCT inherits concepts from the reinforcement learning techniques found in Learning Classifier Systems. Prediction weighted LCT rule evaluation is implemented on a clock cycle scale with low hardware complexity.

Original languageEnglish
Title of host publicationINFORMATIK 2008 - Beherrschbare Systeme - Dank Informatik, Beitrage der 38. Jahrestagung der Gesellschaft fur Informatik e.V. (GI)
Pages771-778
Number of pages8
StatePublished - 2008
Event38th Jahrestagung der Gesellschaft fur Informatik e.V. (GI): Beherrschbare Systeme - Dank Informatik, INFORMATIK 2008 38th Annual Conference of the German Informatics Society (GI): Manageable Systems - Thanks to Computer Science, INFORMATIK 2008 - Munich, Germany
Duration: 8 Sep 200813 Sep 2008

Publication series

NameINFORMATIK 2008 - Beherrschbare Systeme - Dank Informatik, Beitrage der 38. Jahrestagung der Gesellschaft fur Informatik e.V. (GI)
Volume2

Conference

Conference38th Jahrestagung der Gesellschaft fur Informatik e.V. (GI): Beherrschbare Systeme - Dank Informatik, INFORMATIK 2008 38th Annual Conference of the German Informatics Society (GI): Manageable Systems - Thanks to Computer Science, INFORMATIK 2008
Country/TerritoryGermany
CityMunich
Period8/09/0813/09/08

Fingerprint

Dive into the research topics of 'Learning classifier tables for autonomic systems on chip'. Together they form a unique fingerprint.

Cite this