Sciweavers

493 search results - page 95 / 99
» Petri nets design based on neural networks
Sort
View
IJCNN
2006
IEEE
14 years 1 months ago
Reinforcement Learning Control for Biped Robot Walking on Uneven Surfaces
— Biped robots based on the concept of (passive) dynamic walking are far simpler than the traditional fullycontrolled walking robots, while achieving a more natural gait and cons...
Shouyi Wang, Jelmer Braaksma, Robert Babuska, Daan...
GECCO
2003
Springer
100views Optimization» more  GECCO 2003»
14 years 20 days ago
Active Guidance for a Finless Rocket Using Neuroevolution
Finless rockets are more efficient than finned designs, but are too unstable to fly unassisted. These rockets require an active guidance system to control their orientation durin...
Faustino J. Gomez, Risto Miikkulainen
CAIP
2009
Springer
114views Image Analysis» more  CAIP 2009»
13 years 10 months ago
Decision Trees Using the Minimum Entropy-of-Error Principle
Binary decision trees based on univariate splits have traditionally employed so-called impurity functions as a means of searching for the best node splits. Such functions use estim...
Joaquim Marques de Sá, João Gama, Ra...
FLAIRS
2008
13 years 9 months ago
Using Genetic Programming to Increase Rule Quality
Rule extraction is a technique aimed at transforming highly accurate opaque models like neural networks into comprehensible models without losing accuracy. G-REX is a rule extract...
Rikard König, Ulf Johansson, Lars Niklasson
GECCO
2011
Springer
264views Optimization» more  GECCO 2011»
12 years 11 months ago
Critical factors in the performance of novelty search
Novelty search is a recently proposed method for evolutionary computation designed to avoid the problem of deception, in which the fitness function guides the search process away...
Steijn Kistemaker, Shimon Whiteson