8 search results - page 1 / 2 » Training Reformulated Product Units in Hybrid Neural Network... |
IJCNN
2006
IEEE
13 years 11 months ago
2006
IEEE
— Higher order networks allow modelling of correlates and geometrically invariant properties. Current techniques for their development either require domain knowledge, or are con...
IJCNN
2000
IEEE
13 years 9 months ago
2000
IEEE
NPL
2000
13 years 4 months ago
2000
This paper explores internal representation power of product units [1] that act as the functional nodes in the hidden layer of a multi-layer feedforward network. Interesting proper...
SBRN
1998
IEEE
13 years 9 months ago
1998
IEEE
This paper proposes an unsupervised neural algorithm for trajectory production of a 6-DOF robotic arm. The model encodes these trajectories in a single training iteration by using...
GECCO
2007
Springer
13 years 8 months ago
2007
Springer
A primary goal of evolutionary robotics is to create systems that are as robust and adaptive as the human body. Moving toward this goal often involves training control systems tha...