Sciweavers

736 search results - page 2 / 148
» Pruning Neural Networks with Distribution Estimation Algorit...
Sort
View
TNN
1998
111views more  TNN 1998»
13 years 7 months ago
Asymptotic distributions associated to Oja's learning equation for neural networks
— In this paper, we perform a complete asymptotic performance analysis of the stochastic approximation algorithm (denoted subspace network learning algorithm) derived from Oja’...
Jean Pierre Delmas, Jean-Francois Cardos
NIPS
1996
13 years 8 months ago
Early Brain Damage
Optimal Brain Damage (OBD) is a method for reducing the number of weights in a neural network. OBD estimates the increase in cost function if weights are pruned and is a valid app...
Volker Tresp, Ralph Neuneier, Hans-Georg Zimmerman...
ICAI
2007
13 years 8 months ago
Dynamic Programming Algorithm for Training Functional Networks
Abstract— The paper proposes a dynamic programming algorithm for training of functional networks. The algorithm considers each node as a state. The problem is formulated as find...
Emad A. El-Sebakhy, Salahadin Mohammed, Moustafa E...
PPSN
1992
Springer
13 years 11 months ago
Structure Evolution and Incomplete Induction
We present an application of arti cial neural networks to machine condition monitoring. Since several signal preprocessing methods produce high dimensional feature vectors there i...
Reinhard Lohmann
ICANN
2009
Springer
13 years 12 months ago
Statistical Instance-Based Ensemble Pruning for Multi-class Problems
Recent research has shown that the provisional count of votes of an ensemble of classifiers can be used to estimate the probability that the final ensemble prediction coincides w...
Gonzalo Martínez-Muñoz, Daniel Hern&...