Towards Efficient Data Processing on the Edge With Neuromorphic Computing for Instrumentation
Bibliographic record
Abstract
With Moore's law coming to an end and the increasing computational complexity of deep neural network models, a noticeable gap is emerging between the limited computing power available at the edge and the potential of machine learning for instrumentation. Unlike classical deep neural networks, spiking neural networks utilize asynchronous computing and exhibit inherent low-power computing potential, making them ideal for processing large amounts of high-rate event-based data. To showcase this approach, we provide an initial proof of concept that focuses on the CookieBox - an angular streaking detector developed for LCLS-II placed upstream as an online beam diagnostic tool. We utilized a surrogate gradient learning approach to train a basic spiking neural network capable of characterizing individual X-ray pulse using the CookieBox data. The spiking neural network achieves an overall classification accuracy of 86 %, which is comparable to the accuracy achieved by the most recent convolutional neural network performing the same task. We also addressed key elements to enable spiking neural networks capabilities in terms of power and latency requirements for edge machine learning in science experiments. The proposed approach demonstrates and validates that a simple spiking neural network can compete with sophisticated deep neural network and has significant implications for the field of edge machine learning for scientific data acquisition.
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 machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.002 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.001 | 0.002 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.003 | 0.001 |
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 source (direct Gemma or distilled Codex), 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".