Sciweavers

49 search results - page 1 / 10
» Causality and communities in neural networks
Sort
View
ESANN
2007
13 years 6 months ago
Causality and communities in neural networks
A recently proposed nonlinear extension of Granger causality is used to map the dynamics of a neural population onto a graph, whose community structure characterizes the collective...
Leonardo Angelini, Daniele Marinazzo, Mario Pellic...
IJCNN
2000
IEEE
13 years 9 months ago
Bi-Causal Recurrent Cascade Correlation
Recurrent neural networks fail to deal with prediction tasks which do not satisfy the causality assumption. We propose to exploit bi-causality to extend the Recurrent Cascade Corr...
Alessio Micheli, Diego Sona, Alessandro Sperduti
ICANN
2007
Springer
13 years 10 months ago
Information Theoretic Derivations for Causality Detection: Application to Human Gait
As a causality criterion we propose the conditional relative entropy. The relationship with information theoretic functionals mutual information and entropy is established. The con...
Gert Van Dijck, Jo Van Vaerenbergh, Marc M. Van Hu...
ICANN
2010
Springer
13 years 5 months ago
Discovery of Exogenous Variables in Data with More Variables Than Observations
Many statistical methods have been proposed to estimate causal models in classical situations with fewer variables than observations. However, modern datasets including gene expres...
Yasuhiro Sogawa, Shohei Shimizu, Aapo Hyvärin...