Multi-pretrained Deep Neural Network
Neural and Evolutionary Computing
2016-06-03 v1 Machine Learning
Abstract
Pretraining is widely used in deep neutral network and one of the most famous pretraining models is Deep Belief Network (DBN). The optimization formulas are different during the pretraining process for different pretraining models. In this paper, we pretrained deep neutral network by different pretraining models and hence investigated the difference between DBN and Stacked Denoising Autoencoder (SDA) when used as pretraining model. The experimental results show that DBN get a better initial model. However the model converges to a relatively worse model after the finetuning process. Yet after pretrained by SDA for the second time the model converges to a better model if finetuned.
Cite
@article{arxiv.1606.00540,
title = {Multi-pretrained Deep Neural Network},
author = {Zhen Hu and Zhuyin Xue and Tong Cui and Shiqiang Zong and Chenglong He},
journal= {arXiv preprint arXiv:1606.00540},
year = {2016}
}