Empirical Study on the Effect of Residual Networks on the Expressiveness of Linear Regions-Reference-Cited by-同舟云学术

Empirical Study on the Effect of Residual Networks on the Expressiveness of Linear Regions

Published:2023 Issue: Volume: Page:174-185
ISSN:0302-9743
Container-title:Artificial Neural Networks and Machine Learning – ICANN 2023
language:
Short-container-title:

Author:

Qi Xuan^ORCID,Wei Yi^ORCID,Mei Xue^ORCID,Chellali Ryad^ORCID,Yang Shipin^ORCID

Publisher

Springer Nature Switzerland

Link

https://link.springer.com/content/pdf/10.1007/978-3-031-44204-9_15

Reference25 articles.

1. Balduzzi, D., Frean, M., Leary, L., Lewis, J., Ma, K.W.D., McWilliams, B.: The shattered gradients problem: if ResNets are the answer, then what is the question? In: International Conference on Machine Learning, pp. 342–350. PMLR (2017)

2. Chen, H., Wang, Y.G., Xiong, H.: Lower and upper bounds for numbers of linear regions of graph convolutional networks. arXiv preprint arXiv:2206.00228 (2022)

3. Fu, C.Y., Liu, W., Ranga, A., Tyagi, A., Berg, A.C.: DSSD: deconvolutional single shot detector. arXiv preprint arXiv:1701.06659 (2017)

4. Goujon, A., Etemadi, A., Unser, M.: The role of depth, width, and activation complexity in the number of linear regions of neural networks. arXiv preprint arXiv:2206.08615 (2022)

5. Hanin, B., Rolnick, D.: Complexity of linear regions in deep networks. In: International Conference on Machine Learning, pp. 2596–2604. PMLR (2019)

Cited by 1 articles. 订阅此论文施引文献订阅此论文施引文献，注册后可以免费订阅5篇论文的施引文献，订阅后可以查看论文全部施引文献

1. Investigating Translation Invariance and Shiftability in CNNs for Robust Multimedia Forensics: A JPEG Case Study;Proceedings of the 2024 ACM Workshop on Information Hiding and Multimedia Security;2024-06-24