Group <inline-formula> <tex-math notation="LaTeX">$L_{1/2}$ </tex-math></inline-formula> Regularization for Pruning Hidden Layer Nodes of Feedforward Neural Networks

Group <inline-formula> <tex-math notation="LaTeX">$L_{1/2}$ </tex-math></inline-formula> Regularization for Pruning Hidden Layer Nodes of Feedforward Neural Networks

A group L<sub>1/2</sub> regularization term is defined and introduced into the conventional error function for pruning the hidden layer nodes of feedforward neural networks. This group L<sub>1/2</sub> regularization method (GL<sub>1/2</sub>) can prune not only the...

Full description

Bibliographic Details
Main Authors: Habtamu Zegeye Alemu, Junhong Zhao, Feng Li, Wei Wu
Format: Article
Language:English
Published: IEEE 2019-01-01
Series:IEEE Access
Subjects:
Feedforward neural networks
pruning hidden layer nodes and weights
group <italic xmlns:ali="http://www.niso.org/schemas/ali/1.0/" xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance">L</italic>½
smooth group <italic xmlns:ali="http://www.niso.org/schemas/ali/1.0/" xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance">L</italic>½
group lasso
convergence
Online Access:https://ieeexplore.ieee.org/document/8600728/

Internet

https://ieeexplore.ieee.org/document/8600728/

Similar Items