arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2602.07009cs.NEcs.AI
收藏

多尺度时间稳态实现高效且稳健的神经网络

Multi-Scale Temporal Homeostasis Enables Efficient and Robust Neural Networks

MD Azizul Hakim

AI总结:

多尺度时间稳态通过整合不同时间尺度的调节机制,提升人工神经网络的稳定性和效率,适用于多种领域。

摘要:

人工神经网络在基准任务上表现出强大的性能,但在扰动下仍显得脆弱,限制了其在现实世界中的应用。相比之下,生物神经系统通过在多个时间尺度上协调的稳态调节,在数十年中保持稳定的功能。受此启发,本文提出了多尺度时间稳态(MSTH),一种基于生物的框架,将超快(5毫秒)、快(2秒)、中等(5分钟)和慢(1小时)调节整合到人工网络中。MSTH实现了人工神经网络的跨尺度协调系统,提供了一个统一的时间层级,超越了表面的仿生模仿。跨尺度协调通过进化优化机制提高了计算效率。在分子、图和图像分类基准上的实验表明,MSTH一致提高了准确性,消除了灾难性失败,并增强了对扰动的恢复能力。此外,MSTH在单尺度生物启发模型和现有最先进方法上均表现更优,证明了其在不同领域中的通用性。这些发现确立了跨尺度时间协调作为稳定人工神经系统的核心原理,使MSTH成为构建稳健、坚韧和生物忠实智能的基础。

英文摘要:

Artificial neural networks achieve strong performance on benchmark tasks but remain fundamentally brittle under perturbations, limiting their deployment in real-world settings. In contrast, biological nervous systems sustain reliable function across decades through homeostatic regulation coordinated across multiple temporal scales. Inspired by this principle, this presents Multi-Scale Temporal Homeostasis (MSTH), a biologically grounded framework that integrates ultra-fast (5-ms), fast (2-s), medium (5-min) and slow (1-hrs) regulation into artificial networks. MSTH implements the cross-scale coordination system for artificial neural networks, providing a unified temporal hierarchy that moves beyond superficial biomimicry. The cross-scale coordination enhances computational efficiency through evolutionary-refined optimization mechanisms. Experiments across molecular, graph and image classification benchmarks show that MSTH consistently improves accuracy, eliminates catastrophic failures and enhances recovery from perturbations. Moreover, MSTH outperforms both single-scale bio-inspired models and established state-of-the-art methods, demonstrating generality across diverse domains. These findings establish cross-scale temporal coordination as a core principle for stabilizing artificial neural systems, positioning MSTH as a foundation for building robust, resilient and biologically faithful intelligence.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑