L2RU introduces stable state-space models for machine learning and control

Researchers have introduced L2RU, a new class of structured state-space models (SSMs) designed to ensure input-output stability and robustness. This architecture integrates deep learning expressiveness with dynamical systems' interpretability, making it suitable for tasks like system identification and optimal control. L2RU achieves this by incorporating a prescribed L2-gain bound, allowing for unconstrained optimization through standard gradient-based methods while maintaining rigorous stability guarantees. AI

影响 Introduces a novel SSM architecture with guaranteed stability, potentially improving performance and training reliability in control and system identification tasks.

排序理由 This is a research paper introducing a new model architecture.

在 arXiv cs.LG 阅读 →

• L2RU
• Leonardo Massai

• 论文
• 其他

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