Sciweavers

GECCO
2010
Springer
168views Optimization» more  GECCO 2010»
13 years 9 months ago
Investigating whether hyperNEAT produces modular neural networks
HyperNEAT represents a class of neuroevolutionary algorithms that captures some of the power of natural development with a ionally efficient high-level abstraction of development....
Jeff Clune, Benjamin E. Beckmann, Philip K. McKinl...
GECCO
2010
Springer
184views Optimization» more  GECCO 2010»
13 years 9 months ago
Transfer learning through indirect encoding
An important goal for the generative and developmental systems (GDS) community is to show that GDS approaches can compete with more mainstream approaches in machine learning (ML)....
Phillip Verbancsics, Kenneth O. Stanley
GECCO
2010
Springer
182views Optimization» more  GECCO 2010»
13 years 9 months ago
Model selection in genetic programming
Abstract. We discuss the problem of model selection in Genetic Programming using the framework provided by Statistical Learning Theory, i.e. Vapnik-Chervonenkis theory (VC). We pre...
Cruz E. Borges, César Luis Alonso, Jos&eacu...
GECCO
2010
Springer
187views Optimization» more  GECCO 2010»
13 years 9 months ago
The maximum hypervolume set yields near-optimal approximation
In order to allow a comparison of (otherwise incomparable) sets, many evolutionary multiobjective optimizers use indicator functions to guide the search and to evaluate the perfor...
Karl Bringmann, Tobias Friedrich
GECCO
2010
Springer
183views Optimization» more  GECCO 2010»
13 years 9 months ago
Neuroevolution of mobile ad hoc networks
This paper describes a study of the evolution of distributed behavior, specifically the control of agents in a mobile ad hoc network, using neuroevolution. In neuroevolution, a p...
David B. Knoester, Heather Goldsby, Philip K. McKi...
GECCO
2010
Springer
207views Optimization» more  GECCO 2010»
13 years 9 months ago
Generalized crowding for genetic algorithms
Crowding is a technique used in genetic algorithms to preserve diversity in the population and to prevent premature convergence to local optima. It consists of pairing each offsp...
Severino F. Galán, Ole J. Mengshoel
GECCO
2010
Springer
172views Optimization» more  GECCO 2010»
13 years 9 months ago
Designing better fitness functions for automated program repair
Evolutionary methods have been used to repair programs automatically, with promising results. However, the fitness function used to achieve these results was based on a few simpl...
Ethan Fast, Claire Le Goues, Stephanie Forrest, We...
GECCO
2010
Springer
230views Optimization» more  GECCO 2010»
13 years 9 months ago
Exponential natural evolution strategies
The family of natural evolution strategies (NES) offers a principled approach to real-valued evolutionary optimization by following the natural gradient of the expected fitness....
Tobias Glasmachers, Tom Schaul, Yi Sun, Daan Wiers...
GECCO
2010
Springer
159views Optimization» more  GECCO 2010»
13 years 9 months ago
Evolution of division of labor in genetically homogenous groups
Within nature, the success of many organisms, including certain species of insects, mammals, slime molds, and bacteria, is attributed to their performance of division of labor, wh...
Heather Goldsby, David B. Knoester, Charles Ofria