Entropy learning and relevance criteria for neural network pruning
In this paper, entropy is a term used in the learning phase of a neural network. As learning progresses, more hidden nodes get into saturation. The early creation of such hidden nodes may impair generalisation. Hence an entropy approach is proposed to dampen the early creation of such nodes by using...
Saved in:
Main Authors: | Geok, See Ng, Abdul Rahman, Abdul Wahab, Shi, Daming |
---|---|
Format: | Article |
Language: | English |
Published: |
World Scientific Publishing Company
2003
|
Subjects: | |
Online Access: | http://irep.iium.edu.my/38198/1/Entropy_learning_and_relevance_criteria_for_neural_network_pruning.pdf http://irep.iium.edu.my/38198/ http://www.worldscientific.com/doi/abs/10.1142/S0129065703001637 |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Similar Items
-
Entropy learning in neural network
by: Geok, See Ng, et al.
Published: (2003) -
End-to-end supermask pruning: Learning to prune image captioning models
by: Tan, Jia Huei, et al.
Published: (2022) -
Investigation of Data Mining Using Pruned Artificial Neural Network Tree
by: Kalaiarasi, S. M. A., et al.
Published: (2008) -
Network performance of pruned hierarchical torus network
by: Rahman, M.M. Hafizur, et al.
Published: (2009) -
Thermoplastic matrix selection based on entropy method for
importance weight of criteria
by: Sivakumar, Dhar Malingam, et al.
Published: (2016)