Improving deep convolutional neural networks with mixed maxout units.
Motivated by insights from the maxout-units-based deep Convolutional Neural Network (CNN) that "non-maximal features are unable to deliver" and "feature mapping subspace pooling is insufficient," we present a novel mixed variant of the recently introduced maxout unit called a mix...
Main Authors: | Hui-Zhen Zhao, Fu-Xian Liu, Long-Yue Li |
---|---|
Format: | Article |
Language: | English |
Published: |
Public Library of Science (PLoS)
2017-01-01
|
Series: | PLoS ONE |
Online Access: | http://europepmc.org/articles/PMC5519034?pdf=render |
Similar Items
-
Using deep maxout neural networks to improve the accuracy of function prediction from protein interaction networks.
by: Cen Wan, et al.
Published: (2019-01-01) -
A Compound Controller of an Aerial Manipulator Based on Maxout Fuzzy Neural Network
by: Xinchen Qi, et al.
Published: (2020-01-01) -
Evaluation of maxout activations in deep learning across several big data domains
by: Gabriel Castaneda, et al.
Published: (2019-08-01) -
Frequency-Hopping Signal Network-Station Sorting Based on Maxout Network Model and Generative Method
by: Hongguang Li, et al.
Published: (2019-01-01) -
Hierarchical Sparse Coding of Objects in Deep Convolutional Neural Networks
by: Xingyu Liu, et al.
Published: (2020-12-01)