Sciweavers

173 search results - page 5 / 35
» Hierarchy and information in feedforward networks
Sort
View
NIPS
2000
14 years 11 months ago
An Information Maximization Approach to Overcomplete and Recurrent Representations
The principle of maximizing mutual information is applied to learning overcomplete and recurrent representations. The underlying model consists of a network of input units driving...
Oren Shriki, Haim Sompolinsky, Daniel D. Lee
ICNC
2005
Springer
15 years 3 months ago
Segmentation of SAR Image Using Mixture Multiscale ARMA Network
Abstract. A mixture multiscale autoregressive moving average (ARMA) network is proposed for unsupervised segmentation of synthetic aperture radar (SAR) image. The network combines ...
Haixia Xu, Tian Zheng, Fan Meng
ROBOCUP
2004
Springer
138views Robotics» more  ROBOCUP 2004»
15 years 3 months ago
An Algorithm That Recognizes and Reproduces Distinct Types of Humanoid Motion Based on Periodically-Constrained Nonlinear PCA
Abstract. This paper proposes a new algorithm for the automatic segmentation of motion data from a humanoid soccer playing robot that allows feedforward neural networks to generali...
Rawichote Chalodhorn, Karl F. MacDorman, Minoru As...
EUSFLAT
2003
110views Fuzzy Logic» more  EUSFLAT 2003»
14 years 11 months ago
Neuro-finite element static analysis of structures by assembling elemental neuro-modelers
Recently, several algorithms have been proposed for using neural networks in dynamic analysis of small structural systems, and also constructing adaptive material modeling subrout...
Abdolreza Joghataie
TSMC
2002
129views more  TSMC 2002»
14 years 9 months ago
A distributed robotic control system based on a temporal self-organizing neural network
A distributed robot control system is proposed based on a temporal self-organizing neural network, called competitive and temporal Hebbian (CTH) network. The CTH network can learn ...
Guilherme De A. Barreto, Aluizio F. R. Araú...