تقرير
Analyze and Design Network Architectures by Recursion Formulas
| العنوان: | Analyze and Design Network Architectures by Recursion Formulas |
|---|---|
| المؤلفون: | Liao, Yilin, Wang, Hao, Liu, Zhaoran, Li, Haozhe, Liu, Xinggao |
| سنة النشر: | 2021 |
| المجموعة: | Computer Science |
| مصطلحات موضوعية: | Computer Science - Machine Learning, Computer Science - Artificial Intelligence |
| الوصف: | The effectiveness of shortcut/skip-connection has been widely verified, which inspires massive explorations on neural architecture design. This work attempts to find an effective way to design new network architectures. It is discovered that the main difference between network architectures can be reflected in their recursion formulas. Based on this, a methodology is proposed to design novel network architectures from the perspective of mathematical formulas. Afterwards, a case study is provided to generate an improved architecture based on ResNet. Furthermore, the new architecture is compared with ResNet and then tested on ResNet-based networks. Massive experiments are conducted on CIFAR and ImageNet, which witnesses the significant performance improvements provided by the architecture. Comment: It is hoped that the new network architecture is derived according to a specific purpose |
| نوع الوثيقة: | Working Paper |
| URL الوصول: | http://arxiv.org/abs/2108.08689 |
| رقم الأكسشن: | edsarx.2108.08689 |
| قاعدة البيانات: | arXiv |
| الوصف غير متاح. |