SHAP (SHapley Additive exPlanations)
SHAP ni njia ya kueleza miundo, iliyoanzishwa na Scott Lundberg na Su-In Lee mwaka 2017, inayotumia maadili ya Shapley kutoka nadharia ya michezo ya ushirika kupima ni kiasi gani kila kipengele kinachangia utabiri wa mtu binafsi, na kufanya matokeo ya miundo ya akili bandia ya kisanduku cheusi kuwa ya kueleweka. Inasaidia maelezo ya jumla (umuhimu wa kipengele kwa ujumla) na maelezo mahususi (kwa nini utabiri mmoja maalum ulitokea hivyo).
Soma mbinu kamili
Ingia kwa akaunti ya bure ili kusoma sehemu hii.
Method map
The neighbourhood of related methods — select a node to explore.
Vyanzo
- Lundberg, S.M. & Lee, S.-I. (2017). A Unified Approach to Interpreting Model Predictions. Advances in Neural Information Processing Systems, 30, 4766–4777. link ↗
Jinsi ya kunukuu ukurasa huu
ScholarGate. (2026, June 1). SHAP (SHapley Additive exPlanations). ScholarGate. https://scholargate.app/sw/machine-learning/shap-analysis
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.
- Mti wa UamuziUjifunzaji wa Mashine↔ compare
- Mfumo Mchanganyiko wa GaussiaUjifunzaji wa Mashine↔ compare
- Regresheni ya LogistikiTakwimu za Utafiti↔ compare
- Msitu NasibuUjifunzaji wa Mashine↔ compare
- XGBoostUjifunzaji wa Mashine↔ compare
Imerejelewa na
Umeona tatizo kwenye ukurasa huu? Ripoti au pendekeza marekebisho →