Sciweavers

52 search results - page 6 / 11
» Dynamics of Learning Near Singularities in Layered Networks
Sort
View
NECO
2007
127views more  NECO 2007»
13 years 7 months ago
Visual Recognition and Inference Using Dynamic Overcomplete Sparse Learning
We present a hierarchical architecture and learning algorithm for visual recognition and other visual inference tasks such as imagination, reconstruction of occluded images, and e...
Joseph F. Murray, Kenneth Kreutz-Delgado
ISNN
2007
Springer
14 years 1 months ago
Neural Networks Training with Optimal Bounded Ellipsoid Algorithm
Abstract. Compared to normal learning algorithms, for example backpropagation, the optimal bounded ellipsoid (OBE) algorithm has some better properties, such as faster convergence,...
José de Jesús Rubio, Wen Yu
PAM
2005
Springer
14 years 28 days ago
Self-Learning IP Traffic Classification Based on Statistical Flow Characteristics
A number of key areas in IP network engineering, management and surveillance greatly benefit from the ability to dynamically identify traffic flows according to the applications re...
Sebastian Zander, Thuy T. T. Nguyen, Grenville J. ...
ICC
2007
IEEE
115views Communications» more  ICC 2007»
14 years 1 months ago
Cooperation and Routing in Multi-Hop Networks
— We study the cross-layer problem of combining routing and cooperative diversity in multi-hop, bandwidthconstrained networks with dedicated multiple access. Previous work in coo...
Elzbieta Beres, Raviraj Adve
NC
1998
140views Neural Networks» more  NC 1998»
13 years 8 months ago
Recurrent Neural Networks with Iterated Function Systems Dynamics
We suggest a recurrent neural network (RNN) model with a recurrent part corresponding to iterative function systems (IFS) introduced by Barnsley 1] as a fractal image compression ...
Peter Tiño, Georg Dorffner