Looped SSMs improve time series classification with depth-recurrence

Researchers have introduced Looped SSMs, a novel approach to State Space Models for time series classification. This method enhances performance by applying depth-recurrence, where model blocks are reused across layers, similar to looped transformers. The study also highlights the significant benefits of input reshaping techniques, such as concatenating or flattening timesteps, which further boost accuracy. AI

影响 Introduces novel architectural improvements for time series classification models, potentially enhancing performance in specialized AI applications.

排序理由 The cluster contains a new academic paper detailing a novel model architecture and experimental results. [lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.LG 阅读 →

• Looped SSMs
• LrcSSM
• LRU
• State Space Models

• 论文
• 模型发布

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