Polara-Keras2c: Supporting Vectorized AI Models on RISC-V Edge Devices
Bibliographic record
Abstract
The rise of edge computing has introduced unique challenges for deploying efficient AI solutions in resource-limited environments. While traditional AI frameworks are powerful, they often fall short in meeting the requirements of edge computing, such as low latency, constrained computational power, and energy efficiency. This paper presents Polara-Keras2c, an optimized evolution of Keras2c designed specifically for edge computing. Polara-Keras2c enhances compatibility with bare-metal systems, incorporates RISC-V vector extension optimization, and is customized for the Polara architecture. By converting pre-trained Keras models into optimized C code for bare-metal execution on edge devices, Polara-Keras2c enables advanced AI models to operate efficiently in resource-constrained environments. The framework supports fixed-point arithmetic, achieving a minimal accuracy impact of only 0.03% when tested on the MNIST dataset, and offers a streamlined approach for rapid prototyping. Experimental results reveal that Polara-Keras2c achieves up to 4.81 times faster convolution processing with a$64\times 64$input size compared to scalar processing, significantly enhancing computational efficiency and reducing energy consumption. These capabilities position Polara-Keras2c as a transformative tool in real-time, energy-efficient AI processing for edge devices, pushing forward the evolution of edge computing.
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) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.000 | 0.001 |
| Bibliometrics | 0.000 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.002 |
| Open science | 0.003 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.012 | 0.005 |
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".