选择性更新RNN在效率上匹配Transformer的准确性

作者 PulseAugur 编辑部 · [1 个来源] · 2026-05-01 04:00

研究人员开发了一种新型循环神经网络（RNN），称为选择性更新RNN（suRNNs），它可以高效地处理长序列建模。与在每个时间步都进行更新的传统RNN不同，suRNNs在神经元层面使用二进制开关来学习何时保留记忆，将更新与序列长度解耦。这使得它们能够在冗余区间内保持精确的过去信息，从而在Long Range Arena等基准测试中以更高的效率实现Transformer级别的准确性。 AI

影响为长序列数据提供了比Transformer更高效的替代方案，有可能提高音频和视频处理等领域的性能。

排序理由这是一篇详细介绍新型模型架构的研究论文。

在 arXiv cs.LG 阅读 →

AI 生成摘要 · Google Gemini · 来自 1 个来源。我们如何撰写摘要 →

本文如何被排名

Signal score: 0 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Research; 这是一篇详细介绍新型模型架构的研究论文。
Source corroboration: Single-source cluster; Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics: paper, model release; Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance: High; Clearly on-topic for AI-industry coverage.
Story freshness: 153 days old; Aged out of breaking-news scoring windows; ranking reflects the durable signal from the full source set.

完整方法见我们的编辑标准。

报道来源 [1]

arXiv cs.LG TIER_1 English(EN) · Bojian Yin, Shurong Wang, Haoyu Tan, Sander Bohte, Federico Corradi, Guoqi Li · 2026-05-01 04:00

面向长程序列建模的高效稀疏选择性更新RNN

arXiv:2603.02226v2 Announce Type: replace Abstract: Real-world sequential signals, such as audio or video, contain critical information that is often embedded within long periods of silence or noise. While recurrent neural networks (RNNs) are designed to process such data efficie…

本文如何被排名

报道来源 [1]

面向长程序列建模的高效稀疏选择性更新RNN

相关实体

相关话题