Tsare-tsare
Ƙaddamar da ƙetare hanya ce ta sake ƙima don ƙididdige yadda samfurin zai zama gama gari ga bayanan da ba a gani ba.
Dubawa
It makes better use of limited data and gives a more reliable performance estimate than a single train/test split.
Zurfafa nutsewa
Rarraba jirgin ƙasa ɗaya/raba gwaji ba shi da ƙarfi: maki da kuke samu ya dogara sosai akan waɗanne layuka ne suka faɗo a cikin saitin gwajin. Ƙimar-ƙetare tana gyara wannan ta hanyar juya aikin saitin gwajin. A cikin k-fold cross-validation, kuna raba bayanan zuwa k daidai folds, horar da k-1 daga cikinsu, kimanta a kan ninki-fiti, kuma maimaita k sau don haka kowane jere ana gwada sau ɗaya daidai. Matsakaicin makin k yana samar da ingantaccen kimantawa tare da ma'aunin canji. Zaɓuɓɓukan gama gari sune ninka 5 ko 10. Bambance-bambancen sun haɗa da madaidaitan k-fold (kiyaye adadin aji don bayanan da ba daidai ba), barin-daya-fita (k yayi daidai da adadin samfuran), da rarrabuwar tsarin lokaci waɗanda ba su taɓa yin horo kan gaba don hasashen abin da ya gabata ba.
Fahimtar Fasaha
Tabbatar da giciye yana da ƙarfi don zaɓin ƙirar ƙira da kunna hyperparameter: kuna kwatanta jeri ta matsakaicin ƙimar ingancin su maimakon wuce gona da iri zuwa tsaga. Matsala mai mahimmanci shine yoyon bayanai - duk wani tsari wanda ya 'gani' duk saitin bayanai (ƙira, zaɓin fasalin, ƙididdigewa) dole ne ya dace a cikin kowane nau'i, ba kafin rarrabuwa ba, ko ƙimar ku za ta kasance cikin kyakkyawan fata. Ƙididdiga ta giciye ta raba daidaitawa da ƙima ta ƙarshe don guje wa wannan ɗigo.
Dabarun Tasiri
Shawarwari masu haske
Yana taimaka muku keɓance bayyanannen da'awar fasaha daga harshen talla.
Kudin da kasafin kuɗi
Kuna iya yin mafi kyawun tambayoyin aiwatarwa kafin kashe kuɗi ko lokaci.
Ƙungiya da aikin aiki
Ƙungiyoyin da ke da fahimtar juna suna yin mafi kyawun samfura, manufofi, da yanke shawara na koyo.
Makomar Tabbatarwar Giciye
Yayin da saitin bayanai da ƙira ke girma, gudanar da cikakken kewayon horarwa ya zama tsada, don haka masu yin aiki suna ƙara fifita saiti mai girma guda ɗaya da aka gudanar don zurfafa koyo yayin da suke tanadin tabbatarwa ga ƙanana ko tambura bayanai. ML mai sarrafa kansa da kayan aikin kamar scikit-learn's GridSearchCV da Optuna gasa-giciye cikin binciken hyperparameter ta tsohuwa. Ana ci gaba da bincike kan ƙima mai rahusa, bututun da ke jure ɗigo, da ingantacciyar ingantacciyar hanyar haɗaɗɗiya, matsayi, da bayanan da suka dogara da lokaci.
Aiwatar da Gaskiyar Duniya
Yin amfani da ingantaccen giciye mai ninki 5 don kwatanta koma bayan dabaru, dajin bazuwar, da haɓakar gradient kafin ƙaddamar da ƙira ɗaya.
Aiwatar da ƙayyadaddun k-ninka akan saitin bayanan gano zamba mara daidaituwa don haka kowane ninki yana kiyaye kusan daidai gwargwado.
Gudun GridSearchCV ko RandomizedSearchCV, wanda ke haɓaka kowane haɗin hyperparameter don zaɓar mafi kyawun saituna.
Yin amfani da jerin lokaci (mirgina / sarkar gaba) tabbatarwa ta giciye don kimanta haja ko ma'aunin buƙatu ba tare da horo kan bayanai na gaba ba.
Hatsari & Tsare-tsare
Ƙungiyoyi daban-daban na iya amfani da kalmar iri ɗaya daban, don haka ayyana iyaka da wuri.
Alamomi na iya yin kama da ƙarfi yayin da aikin zahirin duniya bai yi daidai ba.
Yin watsi da ingancin bayanai da tsare-tsaren kimantawa galibi yana haifar da sakamako mara ƙarfi.
Taswirar Hanya
Fara da ma'anar harshe a sarari na sakamakon da kuke buƙata.
Zaɓi ma'aunin nasara ɗaya da yanayin gazawa ɗaya kafin gwaji.
Gudun ƙaramin matukin jirgi tare da bayanan wakilci, ba saitin demo da aka goge ba.
Takaddun bayanai inda Tabbatarwar Cross-Validation ke taimakawa kuma inda hanyoyin mafi sauƙi suka fi kyau.
Ci gaba da Bincike
Free newsletter
Get the daily AI briefing
Three verified AI stories every weekday morning, written in plain English. Free forever, no ads.
One email each weekday. Unsubscribe in one click. We never sell or share your address.
Test yourself
Take the Cross-Validation quiz
Instant feedback on every answer, and a shareable certificate with a verifiable ID once you pass a course.
Support free AI education. AI Understanding is a 501(c)(3) nonprofit — no ads, no paywall, ever. Make a donation
Jagora na gaba
Cross-Encoders vs Bi-Encoders
Tambayoyin da ake yawan yi
What is Cross-Validation?
Ƙaddamar da ƙetare hanya ce ta sake ƙima don ƙididdige yadda samfurin zai zama gama gari ga bayanan da ba a gani ba. Yana yin amfani da ƙayyadaddun bayanai kuma yana ba da ingantaccen kimanta aiki fiye da rarrabuwar jirgin ƙasa/gwaji guda ɗaya.
A daidaitaccen ƙimar k-fold giciye, sau nawa ake amfani da kowane ma'aunin bayanai don gwaji?
Kowane ninki yana aiki azaman gwajin da aka saita daidai sau ɗaya a duk zagayen k, don haka kowane samfurin ana gwada shi sau ɗaya kuma ana horar da shi akan sauran.
Menene babban fa'idar k-fold cross-validation akan jirgin ƙasa guda ɗaya/ragawar gwaji?
Ta hanyar maƙasudi sama da ninki biyu, tabbatar da giciye yana rage bambance-bambancen kimanta aikin idan aka kwatanta da dogaro da rarrabuwa ɗaya ta sabani.
Me yasa tabbatarwar k-ninka na yau da kullun bai dace ba don tsinkayar jeri-lokaci?
Canja bayanan da aka ba da oda na lokaci yana ba da gaba cikin horo, don haka jerin lokaci CV yana amfani da rarrabuwar sarkar gaba wanda kawai horarwa akan abubuwan da suka gabata.