按年被提到
20192019 · 1 次2026
机器学习与深度学习›神经网络架构探索·arXiv:1904.01569 · cs.CV

Exploring Randomly Wired Neural Networks for Image Recognition

Saining Xie, Alexander Kirillov, Ross Girshick, Kaiming He · 2019
开始阅读 ↗PDFalphaXiv 讨论
被提及 · 2 人首次 2019-04-05 · 最近 2021-03-19
2不同的人
2活跃月份
2讨论串
355被引(OpenAlex)
arXiv 摘要(候选层不写导读)

Neural networks for image recognition have evolved through extensive manual design from simple chain-like models to structures with multiple wiring paths. The success of ResNets and DenseNets is due in large part to their innovative wiring plans. Now, neural architecture search (NAS) studies are exploring the joint optimization of wiring and operation types, however, the space of possible wirings is constrained and still driven by manual design despite being searched. In this paper, we explore a more diverse set of connectivity patterns through the lens of randomly wired neural networks. To do this, we first define the concept of a stochastic network generator that encapsulates the entire network generation process. Encapsulation provides a unified view of NAS and randomly wired networks. Then, we use three classical random graph models to generate randomly wired graphs for networks. The results are surprising: several variants of these random generators yield network instances that have competitive accuracy on the ImageNet benchmark. These results suggest that new efforts focusing on designing better network generators may lead to new breakthroughs by exploring less constrained search spaces with more room for novel design.

候选层:至少 2 个不同的人、在 2 个不同月份提到过,还没到主书架的 3 人 3 个月。没有做立场标注,所以只写“被提及”。

HN 书评

推荐在前,同类按时间 · 每篇最多保留 20 条,统计用全部提及
评论nujrabes · 2021-03

“Haven't heard the term "freely wired" before, but FAIR released an exploration of randomly wired neural networks which seems conceptually similar. https://arxiv.org/abs/1904.01569”

Freewire: An Experiment with Freely Wired Neural Networks原评论 ↗
被提交为 story · 1 次