MEVZU N°128ISTANBULYEAR I — VOL. III
MEVZU N° TAG / VOL. 040
#compression
0 blog · 0 news · 3 wiki
§03
03Wiki
§01Glossary
Pruning
Removing weights with negligible impact to shrink a model and speed it up.
- EN
- Pruning
- TR
- Budama (Pruning)
§02Glossary
Knowledge Distillation
Training a smaller 'student' model to mimic the behaviour of a larger 'teacher' model.
- EN
- Knowledge Distillation
- TR
- Bilgi Damıtma
§03Glossary
Quantization
Representing model weights with lower-precision numbers to save memory and gain speed.
- EN
- Quantization
- TR
- Niceleme