Difference between revisions of "LightR"
Jump to navigation
Jump to search
m (Design principle & Plans) |
m |
||
| Line 13: | Line 13: | ||
; Planned experiments | ; Planned experiments | ||
: Multiple hand-tuned surfing models -> Expert network & gate network | : Multiple hand-tuned surfing models -> Expert network & gate network | ||
| − | : | + | : Hand-crafted features with naive KNN -> Search-based sequence model |
| − | : Slow networks -> Knowedge | + | : Slow networks -> Knowedge distill & Quantization aware training |
Revision as of 09:14, 11 February 2022
- LightR Sub-pages:
- Version History
This page is under construction. For recent activities, see Version History.
- Design principle
- Strategy light, machine learning heavy.
- Planned experiments
- Multiple hand-tuned surfing models -> Expert network & gate network
- Hand-crafted features with naive KNN -> Search-based sequence model
- Slow networks -> Knowedge distill & Quantization aware training
