Title | ||
---|---|---|
Group L Regularization for Pruning Hidden Layer Nodes of Feedforward Neural Networks. |
Abstract | ||
---|---|---|
A group L-1(/2) regularization term is defined and introduced into the conventional error function for pruning the hidden layer nodes of feedforward neural networks. This group L-1(/2) regularization method (GL(1/2)) can prune not only the redundant hidden nodes but also the redundant weights of the surviving hidden nodes of the neural networks. As a comparison, the popular group lasso regularization (GL(2)) can prune the redundant hidden nodes, but cannot prune any redundant weights of the surviving hidden nodes, of the neural networks. A disadvantage of the GL(1/2) is that it involves a non-smooth absolute value function, which causes oscillation in the numerical computation and difficulty in the convergence analysis. As a remedy, the absolute value function is approximated by a smooth function, resulting in a smooth group L-1(/2) regularization method (SGL(1/2)). Numerical simulations on a few benchmark data sets show that, compared with GL(2), SGL(1/2) can achieve better accuracy and remove more redundant nodes and weights of the surviving hidden nodes. A convergence theorem is also proved for SGL(1/2). |
Year | DOI | Venue |
---|---|---|
2019 | 10.1109/ACCESS.2018.2890740 | IEEE ACCESS |
Keywords | DocType | Volume |
Feedforward neural networks,pruning hidden layer nodes and weights,group L-1(/2),smooth group L-1/2,group lasso,convergence | Journal | 7 |
ISSN | Citations | PageRank |
2169-3536 | 1 | 0.38 |
References | Authors | |
0 | 4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Habtamu Zegeye Alemu | 1 | 3 | 0.74 |
Junhong Zhao | 2 | 27 | 7.02 |
Feng Li | 3 | 3 | 1.09 |
Wei Wu | 4 | 9 | 3.64 |