Sciweavers

462 search results - page 37 / 93
» Verifying Properties of Neural Networks
Sort
View
JCP
2007
100views more  JCP 2007»
13 years 7 months ago
Extraction of Unique Independent Components for Nonlinear Mixture of Sources
—In this paper, a neural network solution to extract independent components from nonlinearly mixed signals is proposed. Firstly, a structurally constrained mixing model is introd...
Pei Gao, Li Chin Khor, Wai Lok Woo, Satnam Singh D...
JMLR
2008
188views more  JMLR 2008»
13 years 7 months ago
Maximal Causes for Non-linear Component Extraction
We study a generative model in which hidden causes combine competitively to produce observations. Multiple active causes combine to determine the value of an observed variable thr...
Jörg Lücke, Maneesh Sahani
NC
2007
123views Neural Networks» more  NC 2007»
13 years 7 months ago
The complexity of latching transitions in large scale cortical networks
Abstract. We study latching dynamics, i.e. the ability of a network to hop spontaneously from one discrete attractor state to another, which has been proposed as a model of an inï¬...
Emilio Kropff, Alessandro Treves
ICONIP
2010
13 years 5 months ago
Emergence of Highly Nonrandom Functional Synaptic Connectivity Through STDP
Abstract. We investigated the network topology organized through spike-timingdependent plasticity (STDP) using pair- and triad-connectivity patterns, considering di erence of excit...
Hideyuki Kato, Tohru Ikeguchi
ICDE
2007
IEEE
198views Database» more  ICDE 2007»
14 years 1 months ago
A Novel Visual Feature Extraction and Its Application in Vowel Recognition
Speech recognition techniques have been developed dramatically in recent years. Nevertheless, errors caused by environmental noise are still a serious problem in recognition. Empl...
Vahideh Sadat Sadeghi, Khashayar Yaghmaie