Experimental validation for N-ary error correcting output codes for ensemble learning of deep neural networks

2018 ◽  
Vol 52 (2) ◽  
pp. 367-392 ◽  
Author(s):  
Kaikai Zhao ◽  
Tetsu Matsukawa ◽  
Einoshin Suzuki
Keyword(s):  
Neural Networks ◽  
Ensemble Learning ◽  
Experimental Validation ◽  
Deep Neural Networks ◽  
Error Correcting Output Codes

Multimodal Deep Neural Networks Based Ensemble Learning for X-Ray Object Recognition

2019 ◽  
pp. 523-538
Author(s):  
Quan Kong ◽  
Naoto Akira ◽  
Bin Tong ◽  
Yuki Watanabe ◽  
Daisuke Matsubara ◽  
...  
Keyword(s):  
Neural Networks ◽  
Object Recognition ◽  
Ensemble Learning ◽  
Deep Neural Networks ◽  
X Ray

scholarly journals Regularizing Deep Neural Networks with an Ensemble-based Decorrelation Method

2018 ◽  
Author(s):  
Shuqin Gu ◽  
Yuexian Hou ◽  
Lipeng Zhang ◽  
Yazhou Zhang
Keyword(s):  
Neural Networks ◽  
Ensemble Learning ◽  
Convolutional Neural Networks ◽  
Deep Neural Networks ◽  
Experimental Results ◽  
Excellent Performance ◽  
Hidden Layer ◽  
Base Learner ◽  
Fully Connected

Although Deep Neural Networks (DNNs) have achieved excellent performance in many tasks, improving the generalization capacity of DNNs still remains a challenge. In this work, we propose a novel regularizer named Ensemble-based Decorrelation Method (EDM), which is motivated by the idea of the ensemble learning to improve generalization capacity of DNNs. EDM can be applied to hidden layers in fully connected neural networks or convolutional neural networks. We treat each hidden layer as an ensemble of several base learners through dividing all the hidden units into several non-overlap groups, and each group will be viewed as a base learner. EDM encourages DNNs to learn more diverse representations by minimizing the covariance between all base learners during the training step. Experimental results on MNIST and CIFAR datasets demonstrate that EDM can effectively reduce the overfitting and improve the generalization capacity of DNNs  

Construction of Error Correcting Output Codes for Robust Deep Neural Networks Based on Label Grouping Scheme

2021 ◽  
Author(s):  
Hwiyoung Youn ◽  
Soonhee Kwon ◽  
Hyunhee Lee ◽  
Jiho Kim ◽  
Songnam Hong ◽  
...  
Keyword(s):  
Neural Networks ◽  
Deep Neural Networks ◽  
Error Correcting Output Codes
Sign in / Sign up

Export Citation Format

Share Document