Hypernetwork-Based Implicit Posterior Estimation and Model Averaging of CNN

Abstract

Deep neural networks have a rich ability to learn complex representations and achieved remarkable results in various tasks. However, they are prone to overfitting due to the limited number of training samples; regularizing the learning process of neural networks is critical. In this paper, we propose a novel regularization method, which estimates parameters of a large convolutional neural network as implicit probabilistic distributions generated by a hypernetwork. Also, we can perform model averaging to improve the network performance. Experimental results demonstrate our regularization method outperformed the commonly-used maximum a posterior (MAP) estimation.

Cite

Text

Ukai et al. "Hypernetwork-Based Implicit Posterior Estimation and Model Averaging of CNN." Proceedings of The 10th Asian Conference on Machine Learning, 2018.

Markdown

[Ukai et al. "Hypernetwork-Based Implicit Posterior Estimation and Model Averaging of CNN." Proceedings of The 10th Asian Conference on Machine Learning, 2018.](https://mlanthology.org/acml/2018/ukai2018acml-hypernetworkbased/)

BibTeX

@inproceedings{ukai2018acml-hypernetworkbased,
  title     = {{Hypernetwork-Based Implicit Posterior Estimation and Model Averaging of CNN}},
  author    = {Ukai, Kenya and Matsubara, Takashi and Uehara, Kuniaki},
  booktitle = {Proceedings of The 10th Asian Conference on Machine Learning},
  year      = {2018},
  pages     = {176-191},
  volume    = {95},
  url       = {https://mlanthology.org/acml/2018/ukai2018acml-hypernetworkbased/}
}