Sciweavers

370 search results - page 38 / 74
» TRUST-TECH Based Neural Network Training
Sort
View
ICANN
2010
Springer
13 years 7 months ago
The Support Feature Machine for Classifying with the Least Number of Features
We propose the so-called Support Feature Machine (SFM) as a novel approach to feature selection for classification, based on minimisation of the zero norm of a separating hyperplan...
Sascha Klement, Thomas Martinetz
ISCI
2008
95views more  ISCI 2008»
13 years 8 months ago
Modified constrained learning algorithms incorporating additional functional constraints into neural networks
In this paper, two modified constrained learning algorithms are proposed to obtain better generalization performance and faster convergence rate. The additional cost terms of the ...
Fei Han, Qing-Hua Ling, De-Shuang Huang
ICANN
1997
Springer
14 years 1 months ago
A Feature Map Approach to Pose Estimation Based on Quaternions
This paper proposes a novel solution to the problem of pose estimation of three-dimensional objects using feature maps. Our approach relies on quaternions as the mathematical repre...
S. Winkler, Patrick Wunsch, Gerd Hirzinger
CEC
2008
IEEE
14 years 3 months ago
Neuro-evolving maintain-station behavior for realistically simulated boats
— We evolve a neural network controller for a boat that learns to maintain a given bearing and range with respect to a moving target in the Lagoon 3D game environment. Simulating...
Nathan A. Penrod, David Carr, Sushil J. Louis, Bob...
ECAI
2000
Springer
14 years 20 days ago
Learning Efficiently with Neural Networks: A Theoretical Comparison between Structured and Flat Representations
Abstract. We are interested in the relationship between learning efficiency and representation in the case of supervised neural networks for pattern classification trained by conti...
Marco Gori, Paolo Frasconi, Alessandro Sperduti