A Versatile Edge Machine Learning Test Bench for High Bandwidth Instrumentation
Bibliographic record
Abstract
New scientific experiments and instruments generate large volumes of data that need to be transferred to storage or processing. Edge machine learning could allow us to reduce the amount of data before transmission, thus reducing the cost of experiments. Data compression can be done in various ways depending on the targeted experiment such as image compression or rejection of unwanted events using a veto system. The high throughput, complexity and operational costs of the instruments make debugging in the real system a difficult challenge. To facilitate debugging and caracterisation of edge machine learning systems, we developed a test bench that can be used for fast testing using both simulated and measured data. This paper details this test bench and the methodology used for caracterizing the performance of a real time data compression system based on an FPGA. In our current configuration, the test bench acquires 51.2 Gbps from a 6.4 GSps analog to digital converter and is designed to integrate data pre-processing and machine learning inside an FPGA. All elements are modular and this test bench could be used for analog or digital detectors but also time to digital converters based systems.
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 | 0.003 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.002 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.010 | 0.002 |
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".