Intrinsic Numerical Robustness and Fault Tolerance in a Neuromorphic Algorithm for Scientific Computing

Bradley H. Theilman; James B. Aimone

cs.NEMar 10, 2026

Intrinsic Numerical Robustness and Fault Tolerance in a Neuromorphic Algorithm for Scientific Computing

Authors: Bradley H. Theilman, James B. Aimone

Organizations: Neural Exploration & Research Laboratory, Sandia National Laboratories, Albuquerque, NM

Abstract

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.

Figures & tables

Fig. 1: Finite element mesh on unit square domain $\Omega$ , and the solution to the example PDE.

Fig. 2: Ablating neurons. Top: Unmodified NeuroFEM raster plot solving the example problem. Shown are spike trains from 50 randomly chosen neurons across the mesh. Bottom: NeuroFEM raster plot with 40% of the neurons ablated.

Fig. 3: Relative error as a function of percent ablated neurons. Overall accuracy is unchanged until the proportion of ablated neurons reaches a threshold that depends on the number of neurons per mesh node (NPM). Increasing the redundancy by increasing the number of neurons per mesh node increases this threshold. Here, $N$ indicates the number of elements in the mesh and the size of the linear system. The total number of neurons in the circuit is $N\times\textsc{NPM}$ . Error bars indicate standard error of the mean over 5 trials.

Fig. 4: Left: NeuroFEM solutions with 50% neurons ablated. Despite clear errors at some mesh nodes, the overall solution remains close to the true solution. Right: Difference between the true and ablated NeuroFEM solutions. Error is concentrated to a few mesh nodes where, by chance, too many neurons were ablated.

Fig. 5: Dropping spikes. Top: Unmodified NeuroFEM raster plot solving the example problem. 50 randomly chosen neurons across the mesh are shown. Bottom: NeuroFEM raster plot with 90% spikes dropped. Individual neurons recalibrate their firing to maintain solution accuracy. Dropping spikes acts like a regularizer leading to sparser activity, which may lead to a neuromorphic advantage.

Fig. 6: Relative error as a function of the proportion of spikes dropped on each timestep. Up to $\sim$ 90% of spikes may be dropped on each timestep before the network shows an appreciable loss in accuracy for this example problem. Again, increasing the redundancy increases the robustness. Error bars indicate standard error of the mean over 5 trials.

Neuromorphic Computing

Neuromorphic computing uses brain-inspired, event-driven algorithms and hardware to process information with low power and latency.

See all 192 papers

Migrate Computation, Not Data: Fault Recovery in Neuromorphic Many-Core Systems
Oct 19, 2026Muyang Cao, Di Yu, Peiling Zhu +4Neuromorphic Computing
Zhejiang University, Hangzhou, China · Southern University of Science and Technology, Shenzhen, China
Bio-plausible Neuromorphic Disturbance Observer Based on Emulation Theory: Extended Version
May 5, 2026Hongfu Xu, Xiaoyu Guo, Shengbo Wang +1Feedback Control Adaptive Control
School of Automation Science and Electrical Engineering, Beihang University, Beijing 100191, China · Department of Mechanical Engineering, City University of Hong Kong, Hong Kong · Department of Electrical and Electronic Engineering, The University of Hong Kong, Hong Kong +1
Dual-axis attribution of zebrafish tectal microcircuits for energy-efficient and robust neurocomputing
May 13, 2026Ningping Li, Hao Zhang, Yi ZhouEfficient Neural Network Inference Neural Processes
University of Science and Technology of China, Hefei, China

Oct 19, 2026J/K move · Enter open · S save

Migrate Computation, Not Data: Fault Recovery in Neuromorphic Many-Core Systems

Muyang Cao, Di Yu, Peiling Zhu, Linshan Jiang+3

Zhejiang University, Hangzhou, China · Southern University of Science and Technology, Shenzhen, China

Neuromorphic Computing

Open paper AskPDF arXiv

As neuromorphic systems scale to thousands of near-memory cores, aging-induced permanent faults in neuron-update datapaths become an important obstacle to long-term deployment. Existing online recovery methods typically retire a faulty core and migrate its neurons, along with their weights and membrane states, to healthy cores. This whole-core treatment incurs high recovery traffic and makes recovery depend on scarce destinations; at high utilization, there may be enough surviving compute capacity but insufficient free storage to copy the affected neuron context. This paper presents SpikeRelay, an online recovery framework for diagnosed compute-unit faults. SpikeRelay exploits the fact that, in many neuromorphic cores, the compute datapath, local SRAM, and router are distinct modules: a compute fault need not destroy stored weights and states or disconnect the core from the NoC. Instead of retiring a faulty core and migrating its neuron data, SpikeRelay converts the faulty core into a storage-and-forwarding node while offloading neuron-update computation to a healthy rescue core. This decoupling of storage and computation eliminates recovery-time data migration and greatly reduces spare-SRAM requirements. Consequently, SpikeRelay sustains 100% recovery at 92.2% SRAM utilization and a 50% fault rate, whereas the best baseline achieves only 22.1%.

Abstract

Neuromorphic Computing

Explore similar work

Migrate Computation, Not Data: Fault Recovery in Neuromorphic Many-Core Systems

Bio-plausible Neuromorphic Disturbance Observer Based on Emulation Theory: Extended Version

Dual-axis attribution of zebrafish tectal microcircuits for energy-efficient and robust neurocomputing