| Virual Oral Presentation Slide by Slide |
IEEE/ICACT20260019 Slide.16
[Big Slide]
[YouTube] |
Oral Presentation |
|
|
K-Nearest Neighbors (KNN) achieves high classification accuracy on the benchmark dataset. However, its distance-based inference requires comparison with multiple stored samples, resulting in high per-sample inference latency. This computational cost makes KNN unsuitable for real-time SmartNIC deployment, despite strong accuracy performance. | |
| [Go to Next Slide] |