Sciweavers

399 search results - page 50 / 80
» Parallel evolutionary algorithms can achieve super-linear pe...
Sort
View
SPAA
2009
ACM
14 years 8 months ago
A lightweight in-place implementation for software thread-level speculation
Thread-level speculation (TLS) is a technique that allows parts of a sequential program to be executed in parallel. TLS ensures the parallel program's behaviour remains true ...
Cosmin E. Oancea, Alan Mycroft, Tim Harris
EH
2002
IEEE
112views Hardware» more  EH 2002»
14 years 18 days ago
Evolving Circuits in Seconds: Experiments with a Stand-Alone Board-Level Evolvable System
The purpose of this paper is twofold: first, to illustrate a stand-alone board-level evolvable system (SABLES) and its performance, and second to illustrate some problems that occ...
Adrian Stoica, Ricardo Salem Zebulum, Michael I. F...
DAC
1999
ACM
13 years 12 months ago
Reducing Cross-Coupling Among Interconnect Wires in Deep-Submicron Datapath Design
As the CMOS technology enters the deep submicron design era, the lateral inter-wire coupling capacitance becomes the dominant part of load capacitance and makes RC delay on the bu...
Joon-Seo Yim, Chong-Min Kyung
CORR
2006
Springer
94views Education» more  CORR 2006»
13 years 7 months ago
Fitness Uniform Optimization
Abstract-- In evolutionary algorithms, the fitness of a population increases with time by mutating and recombining individuals and by a biased selection of more fit individuals. Th...
Marcus Hutter, Shane Legg
PPSN
2010
Springer
13 years 5 months ago
Feature Selection for Multi-purpose Predictive Models: A Many-Objective Task
The target of machine learning is a predictive model that performs well on unseen data. Often, such a model has multiple intended uses, related to different points in the tradeoff ...
Alan P. Reynolds, David W. Corne, Michael J. Chant...