LIME: Maelezo Yanayoweza Kufasiriwa Kienyeji Kwa Kila Mfumo
LIME, iliyoanzishwa na Ribeiro, Singh, na Guestrin mwaka 2016, inaeleza utabiri wa kisimbuzi chochote cha kisanduku cheusi au kirekebishaji kwa kujenga mfumo rahisi, waaminifu kienyeji unaochukua nafasi ya mfumo mkuu karibu na utabiri mmoja unaovutia. Badala ya kueleza mfumo mkuu, LIME inalenga kwa nini mfano maalum ulipangwa jinsi ulivyopangwa, na kufanya mifumo changamano kama vile mitandao mikuu ya neva na mbinu za kuunganisha ziweze kufasiriwa na watumiaji wa mwisho, wataalamu wa nyanja, na wakaguzi.
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
- Ribeiro, M. T., Singh, S., & Guestrin, C. (2016). "Why should I trust you?": Explaining the predictions of any classifier. ACM SIGKDD, 1135–1144. DOI: 10.1145/2939672.2939778 ↗
Jinsi ya kunukuu ukurasa huu
ScholarGate. (2026, June 2). Local Interpretable Model-agnostic Explanations (LIME). ScholarGate. https://scholargate.app/sw/machine-learning/lime
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.
- Maelezo ya Kinyume (Counterfactual Explanations)Ujifunzaji wa Mashine↔ compare
- Msitu NasibuUjifunzaji wa Mashine↔ compare
Imerejelewa na
Umeona tatizo kwenye ukurasa huu? Ripoti au pendekeza marekebisho →