Dubawa
Sharpness-Aware Minimization (SAM) hanya ce ta ingantawa wacce ke neman ba kawai asara ba amma ƙarancin asara a duk faɗin unguwar ma'aunin nauyi - mafi ƙanƙanta. Flatter minima yakan zama mafi kyawu, don haka SAM sau da yawa yana haɓaka daidaiton gwaji da ƙarfi ba tare da canza ƙirar ƙirar ƙira ba.
Sharpness-Aware Range shine shingen gini na fasaha wanda ke shafar ingancin samfuri, farashin kayayyakin more rayuwa, latency, da aminci a sikeli.
Zurfafa nutsewa
Daidaitaccen horo yana rage hasara a wuri ɗaya a cikin sararin nauyi, amma mafita guda biyu tare da asarar horo iri ɗaya na iya zama daban-daban: mafi ƙarancin 'kaifi' yana zaune a cikin kunkuntar kwari inda ƙananan ƙarancin nauyi ke haɓaka asarar, yayin da mafi ƙarancin 'lebur' yana jure ɓarna kuma yawanci yana haɓaka mafi kyawun bayanan gaibu. SAM, wanda Google masu bincike suka gabatar a cikin 2020, ya bayyana wannan a sarari. A kowane mataki ya fara gano ma'aunin nauyi na kusa (a cikin ƙaramin radius rho) wanda ke haɓaka asarar - maƙwabcin mafi munin yanayi - sannan ya sabunta ma'aunin asali na asali don rage asarar a waccan maƙasudin. Wannan makasudin min-max yana tura haɓakawa zuwa yankuna waɗanda ba su da ƙanƙanta iri ɗaya, suna ba da cikakkiyar fa'ida akan rarrabuwar hoto da ƙari.
Fahimtar Fasaha
Kowane matakin SAM wucewa biyu ne. Da farko, lissafta gradient a ma'aunin halin yanzu kuma ɗauki matakin 'hankali' na girman rho a cikin alƙawarin gradient don isa wurin mafi muni a kusa. Na biyu, lissafta gradient a waccan wuri mai ruɗani kuma amfani da shi don sabunta ma'aunin asali. Radius rho yana sarrafa girman girman unguwar da kuke kariya. Kudin yana kusan wucewa biyu gaba-baya kowane mataki, wanda ke ninka lissafin - babban koma baya mai amfani.
Ƙwararren Ƙwararrun Ƙwararru-Aware
Sharpness-Aware Minimization (SAM) hanya ce ta ingantawa wacce ke neman ba kawai asara ba amma ƙarancin asara a duk faɗin unguwar ma'aunin nauyi - mafi ƙanƙanta. Flatter minima yakan zama mafi kyawu, don haka SAM sau da yawa yana haɓaka daidaiton gwaji da ƙarfi ba tare da canza ƙirar ƙirar ƙira ba. Sharpness-Aware Range shine shingen gini na fasaha wanda ke shafar ingancin samfuri, farashin kayayyakin more rayuwa, latency, da aminci a sikeli. Don gina zurfin fahimta, bi da Sharpness-Aware Minimization a matsayin samfurin aiki, ba fasali ɗaya ba: ayyana sakamakon da ake so, fayyace zato, da raba abin da tsarin zai iya yi da dogaro daga abin da har yanzu ke buƙatar yanke hukunci na ƙwararru.
A aikace, ƙungiyoyi masu ƙarfi masu amfani da Sharpness-Aware Minimization suna haɓaka gine-gine, bayanai, da zaɓin abubuwan more rayuwa tare da dogaro da farashi. Suna rubuta ƙayyadaddun ƙa'idodin nasara, gwaji akan bayanan gaskiya da gudanawar aiki, da jujjuyawar bisa ga tsarin gazawar da aka lura maimakon cin nasara na lokaci ɗaya. Wannan shine inda fahimtar ka'idar ta juya zuwa iyawa mai dorewa a cikin samfura, manufofi, da ayyuka.
Hukunce-hukuncen gine-gine suna haifar da aiki da tsadar aiki na shekaru. A lokaci guda, Haɓaka ma'auni ɗaya na iya ɓoye manyan raunin tsarin. Hanyar da ta fi dacewa ita ce haɗa saurin gwaji tare da horon gudanarwa: gudanar da matukin jirgi, kama shaida, buga rajistan ayyukan yanke shawara, da ci gaba da sabunta abubuwan tsaro kamar yadda halayen ƙira, tsammanin mai amfani, da buƙatun tsari ke tasowa.
Dabarun Tasiri
Hukunce-hukuncen gine-gine suna haifar da aiki da tsadar aiki na shekaru.
Hukunce-hukuncen gine-gine suna haifar da aiki da tsadar aiki na shekaru. A cikin ƙawance masu inganci, ana fassara wannan zuwa ƙa'idodin aiki waɗanda za a iya aunawa, iyakokin ikon mallaka, da kuma bita-da-kullin bita don ƙungiyoyi su iya haɓaka kwarin gwiwa a maimakon ɓata shakku.
Ilimin fasaha yana taimaka wa ƙungiyoyi su zaɓi tari mai kyau, ba kawai sabon abu ba.
Ilimin fasaha yana taimaka wa ƙungiyoyi su zaɓi tari mai kyau, ba kawai sabon abu ba. A cikin ƙawance masu inganci, ana fassara wannan zuwa ƙa'idodin aiki waɗanda za a iya aunawa, iyakokin ikon mallaka, da kuma bita-da-kullin bita don ƙungiyoyi su iya haɓaka kwarin gwiwa a maimakon ɓata shakku.
Zaɓuɓɓukan injiniya mafi kyau suna rage abin dogaro a cikin samarwa.
Zaɓuɓɓukan injiniya mafi kyau suna rage abin dogaro a cikin samarwa. A cikin ƙawance masu inganci, ana fassara wannan zuwa ƙa'idodin aiki waɗanda za a iya aunawa, iyakokin ikon mallaka, da kuma bita-da-kullin bita don ƙungiyoyi su iya haɓaka kwarin gwiwa a maimakon ɓata shakku.
Aiwatar da Gaskiyar Duniya
Haɓaka Mai Canjin hangen nesa da daidaiton ResNet akan ImageNet ta horo tare da SAM maimakon SGD bayyananne.
Haɓaka ƙarfi don yin lakabin amo, tun da ƙananan ƙananan ba su da yuwuwar haddar gurɓatattun takalmi.
Kyawawan tsarin ƙirar harshe da aka riga aka horar da su tare da SAM don samun ingantacciyar fahimta akan ƙananan bayanan bayanan ƙasa.
Amfani da bambance-bambancen ESAM ko LookSAM lokacin da aka ninka lissafin kuɗin vanilla SAM yayi tsada sosai.
Hanyoyin Aiwatarwa
Ragewar Kaifi-Arewa a aikace
Haɓaka Mai Canjin hangen nesa da daidaiton ResNet akan ImageNet ta horo tare da SAM maimakon SGD bayyananne.
Haɓaka Mai Canjin hangen nesa da daidaiton ResNet akan ImageNet ta hanyar horarwa tare da SAM maimakon ƙungiyoyin SGD a sarari yawanci suna samun sakamako mafi kyau lokacin da suka ayyana madaidaicin ƙofofin gaba, kiyaye hanyar haɓaka ɗan adam don ƙararraki, da bin diddigin abubuwan samarwa da ƙimar kuskure akan lokaci.
Ragewar Kaifi-Arewa a aikace
Haɓaka ƙarfi don yin lakabin amo, tun da ƙananan ƙananan ba su da yuwuwar haddar gurɓatattun takalmi.
Haɓaka ƙarfi don lakafta amo, tun da ƙananan ƙananan ba su da yuwuwar haddar gurɓatattun alamomin Ƙungiyoyi yawanci suna samun sakamako mafi kyau lokacin da suka ayyana ma'auni masu inganci a gaba, kiyaye hanyar haɓakar ɗan adam don shari'o'in gefe, da bin duk nasarorin samarwa da ƙimar kuskure akan lokaci.
Ragewar Kaifi-Arewa a aikace
Kyawawan tsarin ƙirar harshe da aka riga aka horar da su tare da SAM don samun ingantacciyar fahimta akan ƙananan bayanan bayanan ƙasa.
Kyawawan tsarin ƙirar harshe da aka riga aka horar da su tare da SAM don samun ingantacciyar haɓakawa akan ƙananan bayanan bayanan ƙasa Ƙungiyoyi yawanci suna samun sakamako mafi kyau lokacin da suka ayyana ƙofofin inganci a gaba, kiyaye hanyar haɓakar ɗan adam don shari'o'i, da bin duk nasarorin samarwa da ƙimar kuskure a kan lokaci.
Ragewar Kaifi-Arewa a aikace
Amfani da bambance-bambancen ESAM ko LookSAM lokacin da aka ninka lissafin kuɗin vanilla SAM yayi tsada sosai.
Yin amfani da bambance-bambancen ESAM ko LookSAM lokacin da aka ninka lissafin kuɗin vanilla SAM yayi tsada sosai Ƙungiyoyi yawanci suna samun sakamako mafi kyau lokacin da suka ayyana ƙofofin inganci a gaba, kiyaye hanyar haɓakar ɗan adam don shari'o'in gefe, da bin duk nasarorin samarwa da ƙimar kuskure akan lokaci.
Hatsari & Tsare-tsare
Haɓaka ma'auni ɗaya na iya ɓoye manyan raunin tsarin.
Sau da yawa ana raina kayan more rayuwa da kuma kuɗin kulawa.
Tsaro da gibin lura na iya girma yayin da tsarin ke ƙara haɓaka.
Taswirar Hanya
Ƙayyade latency, inganci, da maƙasudin farashi kafin aiwatarwa.
Ƙayyade latency, inganci, da maƙasudin farashi kafin aiwatarwa. Ɗauki kowane mataki azaman ƙofar shaida: idan ba a cika sharuɗɗa ba, dakatar da fitar, rufe tazarar, sannan kawai faɗaɗa amfani.
Alamar ma'auni a ƙarƙashin ainihin kaya da yanayin bayanai.
Alamar ma'auni a ƙarƙashin ainihin kaya da yanayin bayanai. Ɗauki kowane mataki azaman ƙofar shaida: idan ba a cika sharuɗɗa ba, dakatar da fitar, rufe tazarar, sannan kawai faɗaɗa amfani.
Kula da kayan aiki don kurakurai, ɗigo, da tasirin mai amfani.
Kula da kayan aiki don kurakurai, ɗigo, da tasirin mai amfani. Ɗauki kowane mataki azaman ƙofar shaida: idan ba a cika sharuɗɗa ba, dakatar da fitar, rufe tazarar, sannan kawai faɗaɗa amfani.
Shirya bijirowa da hanyoyin mayar da martani kafin sikeli.
Shirya bijirowa da hanyoyin mayar da martani kafin sikeli. Ɗauki kowane mataki azaman ƙofar shaida: idan ba a cika sharuɗɗa ba, dakatar da fitar, rufe tazarar, sannan kawai faɗaɗa amfani.