A Node Pruning Algorithm Based on Optimal Brain Surgeon for Feedforward Neural Networks

2006 ◽  
pp. 524-529 ◽  
Author(s):  
Jinhua Xu ◽  
Daniel W. C. Ho
Keyword(s):  
Neural Networks ◽  
Feedforward Neural Networks ◽  
Pruning Algorithm ◽  
Optimal Brain Surgeon

scholarly journals A Pruning Algorithm Based on Relevancy Index of Hidden Neurons Outputs

2016 ◽  
Vol 6 (4) ◽  
pp. 1067-1074
Author(s):  
S. Abid ◽  
M. Chtourou ◽  
M. Djemel
Keyword(s):  
Neural Networks ◽  
Artificial Neural Networks ◽  
Wind Turbine ◽  
Learning Process ◽  
Training Algorithm ◽  
Pruning Algorithm ◽  
Output Amplitude ◽  
Large Application ◽  
Hidden Neurons ◽  
Optimal Brain Surgeon

Choosing the training algorithm and determining the architecture of artificial neural networks are very important issues with large application. There are no general methods which permit the estimation of the adequate neural networks size. In order to achieve this goal, a pruning algorithm based on the relevancy index of hidden neurons outputs is developed in this paper. The relevancy index depends on the output amplitude of each hidden neuron and estimates his contribution on the learning process. This method is validated with an academic example and it is tested on a wind turbine modeling problem. Compared with two modified versions of Optimal Brain Surgeon (OBS) algorithm, the developed approach gives interesting results.

scholarly journals An iterative pruning algorithm for feedforward neural networks

1997 ◽  
Vol 8 (3) ◽  
pp. 519-531 ◽  
Author(s):  
G. Castellano ◽  
A.M. Fanelli ◽  
M. Pelillo
Keyword(s):  
Neural Networks ◽  
Feedforward Neural Networks ◽  
Pruning Algorithm

scholarly journals Research and Application of Improved AGP Algorithm for Structural Optimization Based on Feedforward Neural Networks

2015 ◽  
Vol 2015 ◽  
pp. 1-6
Author(s):  
Ruliang Wang ◽  
Huanlong Sun ◽  
Benbo Zha ◽  
Lei Wang
Keyword(s):  
Neural Networks ◽  
Structural Optimization ◽  
Network Performance ◽  
Feedforward Neural Networks ◽  
Improved Method ◽  
Pruning Algorithm ◽  
Network Pruning ◽  
Internal Relation ◽  
Traffic Capacity ◽  
Simulation Results

The adaptive growing and pruning algorithm (AGP) has been improved, and the network pruning is based on the sigmoidal activation value of the node and all the weights of its outgoing connections. The nodes are pruned directly, but those nodes that have internal relation are not removed. The network growing is based on the idea of variance. We directly copy those nodes with high correlation. An improved AGP algorithm (IAGP) is proposed. And it improves the network performance and efficiency. The simulation results show that, compared with the AGP algorithm, the improved method (IAGP) can quickly and accurately predict traffic capacity.

scholarly journals Asymptotic Prediction Error Variance for Feedforward Neural Networks

2020 ◽  
Vol 53 (2) ◽  
pp. 1108-1113
Author(s):  
Magnus Malmström ◽  
Isaac Skog ◽  
Daniel Axehill ◽  
Fredrik Gustafsson
Keyword(s):  
Neural Networks ◽  
Prediction Error ◽  
Feedforward Neural Networks ◽  
Error Variance ◽  
Prediction Error Variance
Sign in / Sign up

Export Citation Format

Share Document