Sciweavers

28 search results - page 6 / 6
» Transfer functions: hidden possibilities for better neural n...
Sort
View
INFORMS
1998
100views more  INFORMS 1998»
13 years 7 months ago
Feature Selection via Mathematical Programming
The problem of discriminating between two nite point sets in n-dimensional feature space by a separating plane that utilizes as few of the features as possible, is formulated as a...
Paul S. Bradley, Olvi L. Mangasarian, W. Nick Stre...
ICANN
2010
Springer
13 years 6 months ago
Teaching Humanoids to Imitate 'Shapes' of Movements
Trajectory formation is one of the basic functions of the neuromotor controller. In particular, reaching, avoiding, controlling impacts (hitting), drawing, dancing and imitating ar...
Vishwanathan Mohan, Giorgio Metta, Jacopo Zenzeri,...
GECCO
2009
Springer
14 years 10 days ago
The sensitivity of HyperNEAT to different geometric representations of a problem
HyperNEAT, a generative encoding for evolving artificial neural networks (ANNs), has the unique and powerful ability to exploit the geometry of a problem (e.g., symmetries) by enc...
Jeff Clune, Charles Ofria, Robert T. Pennock