Sciweavers

529 search results - page 24 / 106
» Population Training Heuristics
Sort
View
ISCAS
2006
IEEE
90views Hardware» more  ISCAS 2006»
14 years 4 months ago
Feature competition in a spike-based winner-take-all VLSI network
— Recurrent networks and hardware analogs that perform a winner-take-all computation have been studied extensively. This computation is rarely demonstrated in a spiking network o...
Shih-Chii Liu, Matthias Oster
CEC
2010
IEEE
13 years 11 months ago
Multi-objective memetic evolution of ART-based classifiers
In this paper we present a novel framework for evolving ART-based classification models, which we refer to as MOME-ART. The new training framework aims to evolve populations of ART...
Rong Li, Timothy R. Mersch, Oriana X. Wen, Assem K...
CEC
2010
IEEE
13 years 11 months ago
Improving GP classification performance by injection of decision trees
This paper presents a novel hybrid method combining genetic programming and decision tree learning. The method starts by estimating a benchmark level of reasonable accuracy, based ...
Rikard König, Ulf Johansson, Tuve Löfstr...
GECCO
2009
Springer
144views Optimization» more  GECCO 2009»
14 years 4 months ago
Cheating for problem solving: a genetic algorithm with social interactions
We propose a variation of the standard genetic algorithm that incorporates social interaction between the individuals in the population. Our goal is to understand the evolutionary...
Rafael Lahoz-Beltra, Gabriela Ochoa, Uwe Aickelin
GECCO
2008
Springer
107views Optimization» more  GECCO 2008»
13 years 11 months ago
The influence of scaling and assortativity on takeover times in scale-free topologies
In evolving systems, the topological characteristics of population structure have a pronounced impact on the rate of spread of advantageous alleles, and therefore affect selective...
Joshua L. Payne, Margaret J. Eppstein