On Compression of Unsupervised Neural Nets by Pruning Weak Connections
Computer Vision and Pattern Recognition
2021-05-11 v3 Neural and Evolutionary Computing
Abstract
Unsupervised neural nets such as Restricted Boltzmann Machines(RBMs) and Deep Belif Networks(DBNs), are powerful in automatic feature extraction,unsupervised weight initialization and density estimation. In this paper,we demonstrate that the parameters of these neural nets can be dramatically reduced without affecting their performance. We describe a method to reduce the parameters required by RBM which is the basic building block for deep architectures. Further we propose an unsupervised sparse deep architectures selection algorithm to form sparse deep neural networks.Experimental results show that there is virtually no loss in either generative or discriminative performance.
Cite
@article{arxiv.1901.07066,
title = {On Compression of Unsupervised Neural Nets by Pruning Weak Connections},
author = {Zhiwen Zuo and Lei Zhao and Liwen Zuo and Feng Jiang and Wei Xing and Dongming Lu},
journal= {arXiv preprint arXiv:1901.07066},
year = {2021}
}
Comments
This paper needs to be further revised