English(EN) Infinity-norm-based Input-to-State-Stable Long Short-Term Memory networks: a thermal systems perspective

新的LSTM稳定性方法优于现有模型

作者 PulseAugur 编辑部 · [1 个来源] · 2026-06-10 04:00

研究人员开发了一种新方法，用于确保长短期记忆（LSTM）网络在系统辨识中的稳定性，特别是非线性动态系统，如热力学过程。他们的方法基于无穷范数推导出了输入-状态稳定性（ISS）的充分条件，该条件比以前的方法依赖更少的网络参数。该技术已在热力学系统上得到验证，其中ISS促进的LSTM在性能上优于基于物理的模型和其他循环神经网络变体。 AI

影响增强了循环神经网络在复杂动态系统建模方面的可靠性。

排序理由该集群包含一篇学术论文，详细介绍了一种提高LSTM网络稳定性方面的新方法。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv stat.ML 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: Tool; 该集群包含一篇学术论文，详细介绍了一种提高LSTM网络稳定性方面的新方法。[lever_c_demoted from research: ic=1 ai=1.0]
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, other; 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: 120 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 stat.ML TIER_1 English(EN) · Stefano De Carli, Davide Previtali, Leandro Pitturelli, Mirko Mazzoleni, Antonio Ferramosca, Fabio Previdi · 2026-06-10 04:00

基于无穷范数的输入到状态稳定长短期记忆网络：热力学系统视角

arXiv:2503.11553v3 Announce Type: replace-cross Abstract: Recurrent Neural Networks (RNNs) have shown remarkable performances in system identification, particularly in nonlinear dynamical systems such as thermal processes. However, stability remains a critical challenge in practi…

本文如何被排名

报道来源 [1]

基于无穷范数的输入到状态稳定长短期记忆网络：热力学系统视角

相关实体

相关话题