High-dimensional neural feature design for layer-wise reduction of training cost
Abstract We design a rectified linear unit-based multilayer neural network by mapping the feature vectors to a higher dimensional space in every layer. We design the weight matrices in every layer to ensure a reduction of the training cost as the number of layers increases. Linear projection to the...
Main Authors: | , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
SpringerOpen
2020-09-01
|
Series: | EURASIP Journal on Advances in Signal Processing |
Subjects: | |
Online Access: | http://link.springer.com/article/10.1186/s13634-020-00695-2 |