神经形态算法对神经元缺失和脉冲丢失具有强容错能力。
Intrinsic Numerical Robustness and Fault Tolerance in a Neuromorphic Algorithm for Scientific Computing
- 基于脉冲的神经形态算法，通过结构扰动测试验证鲁棒性。
- 可容忍32%神经元缺失、90%脉冲丢失仍保持精度。
- 适合研究脑启发式计算与高可靠性硬件设计的人参考。
神经形态计算具备内在容错潜力，但其在科学计算中的鲁棒性尚未被证实。本文展示了一种此前提出的、原生脉冲的神经形态算法，在求解偏微分方程时，对神经元缺失和脉冲丢失具有内在容错能力。实验表明，即使多达32%的神经元被移除、高达90%的脉冲被丢弃，结果精度仍无显著下降。此外，这种鲁棒性可通过结构超参数调节。该工作证明，算法所借鉴的类脑设计在提升系统稳健性方面发挥了重要作用。
原文摘要 · Abstract (English)
The potential for neuromorphic computing to provide intrinsic fault tolerance has long been speculated, but the brain's robustness in neuromorphic applications has yet to be demonstrated. Here, we show that a previously described, natively spiking neuromorphic algorithm for solving partial differential equations is intrinsically tolerant to structural perturbations in the form of ablated neurons and dropped spikes. The tolerance band for these perturbations is large: we find that as many as 32 percent of the neurons and up to 90 percent of the spikes may be entirely dropped before a significant degradation in the accuracy results. Furthermore, this robustness is tunable through structural hyperparameters. This work demonstrates that the specific brain-like inspiration behind the algorithm contributes to a significant degree of robustness expected from brain-like neuromorphic algorithms.
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。