ScholarGate
Msaidizi
Machine learning

Ufumbuzi wa Maarifa

Ufumbuzi wa Maarifa ni mbinu ya upunguzaji wa modeli, iliyoanzishwa na Geoffrey Hinton na wenzake mwaka 2015, ambayo hufunza modeli ndogo ya mwanafunzi kwa kutumia matokeo ya lebo laini kutoka kwa modeli kubwa ya mwalimu. Modeli zilizofumbuliwa kama vile DistilBERT na TinyBERT hufikia takriban 97% ya utendaji wa modeli kubwa huku zikikimbia kwa kasi zaidi.

Fungua katika MethodMindHivi karibuniVideoHivi karibuniDownload slides

Soma mbinu kamili

Kwa wanachama pekee

Ingia kwa akaunti ya bure ili kusoma sehemu hii.

Ingia

Method map

The neighbourhood of related methods — select a node to explore.

+3 more

Vyanzo

  1. Hinton, G., Vinyals, O. & Dean, J. (2015). Distilling the Knowledge in a Neural Network. NeurIPS Deep Learning Workshop. link
  2. Sanh, V., Debut, L., Chaumond, J. & Wolf, T. (2019). DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter. arXiv:1910.01108. link

Jinsi ya kunukuu ukurasa huu

ScholarGate. (2026, June 1). Knowledge Distillation (Teacher–Student Model Compression). ScholarGate. https://scholargate.app/sw/deep-learning/knowledge-distillation

Which method?

Set this method beside its closest kin and read them side by side — the library lays the books on the table; the choice is yours.

Compare side by side

Imerejelewa na

ScholarGateKnowledge Distillation (Knowledge Distillation (Teacher–Student Model Compression)). Imepatikana 2026-06-15 kutoka https://scholargate.app/sw/deep-learning/knowledge-distillation · Seti ya data: https://doi.org/10.5281/zenodo.20539026