Cutting FLOPs Overhead with SNT and LReSuMe: A Noise-Tolerant Spiking Classifier
Bibliographic record
Abstract
Spiking neural networks (SNNs) operate with discrete spikes, naturally aligning with temporal data and offering sub-milliwatt operation. Their accuracy, however, can collapse when spike timing is perturbed by sensor or environmental noise. We address this vulnerability with two innovations. First, this study introduces a Sensitive Noise-Threshold (SNT), a learnable variable firing threshold that adapts online to the local noise statistics, suppressing spurious spikes while preserving salient ones. Second, this study proposes the Limited Remote Supervised Method (LReSuMe), a lightweight gradient-free rule that supports online learning and enhances spike intensity at the target time. Compared with an equivalently-sized <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$400 \times 10 \text{ANN}$</tex>, the single-layer SNN in this study requires 18% fewer floating-point operations (FLOPs) for inference (6610 vs 8029 FLOPs per sample) and 90% fewer FLOPs for weight update (1200 vs 12030 FLOPs per sample). Despite a marginal 5% drop in peak accuracy, the SNN is 52.79% more accurate than the ANN when 250 random pixels are corrupted, demonstrating a substantial robustness gain under severe noise conditions. These results, obtained entirely in software, indicate that the SNT + LReSuMe framework delivers robust, low-resource online learning; mapping the design onto an FPGA is left as ongoing work for energy-constrained vision sensors.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.000 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.000 | 0.001 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.001 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one teacher head, not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".