LNN比LSTM更高效且抗数据缺失，适合临床等时间敏感场景。
Comparative Analysis of Liquid Neural Networks and LSTM for Sequential Pattern Recognition: Robustness, Efficiency, and Clinical Utility
- 用连续微分方程建模时序，突破传统离散时间步限制。
- 在4个数据集上参数量减少50%以上，缺损数据下准确率仍高20%。
- 特别适合生理信号等稀疏、连续的临床时序任务。
传统循环神经网络（RNN）和长短期记忆（LSTM）以离散时间步运行，难以捕捉真实物理过程的连续动态。液态神经网络（LNN），特别是闭式连续时间（CfC）网络，通过将隐藏状态演化建模为连续微分方程来解决这一问题。本文在四个不同序列模态上进行综合基准测试：类脑事件数据（N-MNIST）、笔画绘图（QuickDraw）、视觉手写（IAM）以及生理时间序列（PhysioNet Sepsis-3）。此外，我们通过时间丢弃法进行严格压力测试，评估模型对缺失数据的鲁棒性。结果表明，LNN在原生时间域和临床环境中始终展现出更高的参数效率与显著更强的鲁棒性，尤其在数据稀疏场景中表现突出。本扩展预印本补充了相关数据集背景与LNN理论脉络，并附详细实现与实验设置文档。
原文摘要 · Abstract (English)
Traditional Recurrent Neural Networks (RNNs) and Long Short-Term Memory (LSTM) units operate on discrete time steps, often failing to capture the fluid temporal dynamics of real-world physical processes. Liquid Neural Networks (LNNs), specifically Closed-form Continuous-time (CfC) networks, address this by modeling the hidden state evolution as a continuous differential equation. In this paper, we conduct a comprehensive benchmarking study across four distinct sequential modalities: neuromorphic event-based data (N-MNIST), stroke-based drawing (QuickDraw), visual handwriting (IAM), and physiological time-series (PhysioNet Sepsis-3). Furthermore, we perform a rigorous stress test using temporal dropout to evaluate model robustness against missing data. Our findings reveal that LNNs consistently provide superior parameter efficiency and significantly higher robustness in natively temporal domains and clinical environments where data sparsity is prevalent. This extended preprint provides additional background on related datasets and the LNN theoretical lineage, supplemented with a detailed appendix documenting our full implementation and experimental settings.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。