01
Gidauniyar AI
Fahimtar abin da AI yake, yadda tsarin ke koya, inda suka kasa, da kuma yadda ake yin hukunci da da'awar ba tare da talla ba.
Laburaren AI kyauta
Na fasaha jagororiKyauta har abada.
177 jagororin turanci a sarari, tsayayyen hanyoyin koyo, da buɗe ɗakin karatu - wanda 501(c)(3) mai zaman kanta ta gina ta yadda kowa zai iya fahimtar AI na zamani.
177Jagoran kyauta
1Waƙoƙin jigo
~2 minKowane jagora
~6hLokacin karatu
Fara a nan
Biyar darussa na tushen sakamako
Kowane darasi ya haɗa da tabbataccen sakamako, ƙwarewar taswira, ayyukan yi, da babban dutse da aka yi amfani da shi.
02
Mai amfani AI mai alhakin
Yi amfani da AI da kyau yayin kare sirri, bincika abubuwan da aka fitar, da kiyaye lissafin ɗan adam.
03
AI a Aiki
Yi ƙididdige shari'o'in amfani da wurin aiki, gudanar da amintattun matukan jirgi, auna ƙima, da sadar da canje-canje cikin gaskiya.
04
Manufar AI & Al'umma
Yi nazarin tsarin AI ta hanyar haƙƙoƙi, daidaito, shugabanci, aminci, da sakamakon amfanin jama'a.
05
Gina tare da AI Systems
Fahimtar ƙirar harshe, maidowa, wakilai, kimantawa, farashi, da tsare-tsaren turawa ta hanyar ƙira mai amfani.
Waƙoƙin jigo
Bincika ta hanya
Tsallaka zuwa yankin da kuke damuwa. Kowace waƙa tana da jagororin bayyanannun Ingilishi da yawa.
Muhimman abubuwaMahimman ra'ayi: yadda AI ke aiki a babban matakin.84 jagorori Harshen AILLMs, NLP, ChatGPT, faɗakarwa, da fahimtar rubutu.155 jagorori Kayayyakin AIƘirƙirar hoto, hangen nesa na kwamfuta, bidiyo, da ƙira.133 jagorori Audio AIMurya, kiɗa, kwasfan fayiloli, da audio-farko AI.117 jagorori KamfanoniBayanan bayanan OpenAI, Anthropic, Google, Meta, da ƙari.121 jagorori Aikace-aikaceYadda AI ke nunawa a cikin coding, bincike, wakilai, da rayuwar yau da kullun.111 jagorori Masana'antuAI a cikin kiwon lafiya, kuɗi, ilimi, makamashi, da ƙari.91 jagorori Na fasahaChips, daidaitawa, RAG, vectors, da kayan aikin AI.177 jagorori Al'ummaBias, keɓantawa, haƙƙin mallaka, aminci, da makomar AI.30 jagorori
Cikakken ɗakin karatu
Duk jagora
177 na 1019 jagororin da aka nuna. Tace ta hanya ko bincike a sama.
Na fasaha
Hankali Maida Hankali da Yanke Kai
Fitar da hankali wata hanya ce ta gano yadda bayanai ke gudana ta cikin ma'aunin hankali na Transformer don bayyana abin da alamun shigarwa ke tasiri…
Na fasahaHaɓaka oda na biyu da hanyoyin Newton
Haɓaka oda na biyu yana amfani da bayanan curvature (matrix Hessian na abubuwan haɓakawa na biyu) don ɗaukar matakai mafi wayo zuwa mafi ƙaranci, ba kawai gangara ba.
Na fasahaRMSNorm da Pre-Layer Normalization
RMSNorm wani yanki ne na daidaita nauyi mai nauyi wanda ke sake daidaita ayyukan ta tushen ma'anar murabba'in su, da wuraren daidaitawa na pre-layer waɗanda ke mataki kafin kowane…
Na fasahaSwiGLU da Ayyukan Gated
SwiGLU aikin kunnawa gated ne wanda ke ninka tsinkayar layi ɗaya na shigarwar ta hanyar tsinkayar Swish-kunna na biyu, yana aiki azaman abin koyo…
Na fasahaCibiyoyin sadarwa na Matsi-da-Haɗa kai
Tubalan Squeeze-and-Excitation (SE) suna barin cibiyar sadarwa mai jujjuyawa ta koyi nawa za ta auna nauyin kowane tasha, ta sake daidaita su bisa yanayin duniya.
Na fasahaJadawalin Warmup da Cosine Annealing
Warmup a hankali yana haɓaka ƙimar koyo daga kusa da sifili kafin horo, sa'an nan kuma cirewar cosine a hankali yana lalatar da shi baya bin lankwasa na cosine.
Na fasahaYawan Koyon Zagaye
Matsakaicin koyo na cyclical akai-akai suna sake zagayowar ƙimar koyo sama da ƙasa tsakanin ƙasa da babba maimakon lalata shi kawai.
Na fasahaRagewar Kaifi-Arewa
Sharpness-Aware Minimization (SAM) hanya ce ingantacciya wacce ke neman ba kawai asara ba amma ƙarancin asara a duk yanki na ma'aunin nauyi - lebur…
Na fasahaƘimar Layi na Layi da Daskararrun Ƙimar Siffar
Binciken linzamin kwamfuta yana gwada yadda kyakkyawan tsarin wakilcin da aka riga aka horar da shi ta hanyar daskare cibiyar sadarwa da horar da madaidaicin madaidaicin layi a saman.
Na fasahaDenseNet da Haɗin Haɗin
DenseNet cibiyar sadarwa ce mai jujjuyawa inda kowane Layer ke karɓar taswirorin fasalulluka na duk matakan da suka gabata azaman shigarwa.
Na fasahaGine-ginen Bottleneck
Gine-gine na ƙwanƙwasa yana matse bayanai ta ƙunƙuntaccen Layer kafin a sake faɗaɗa shi, yana tilastawa hanyar sadarwa ta koyi ƙarami, mai inganci…
Na fasahaRarraba Gradient
Tarin gradient yana ba ku damar kwaikwayi babban girman tsari akan ƙayyadaddun ƙwaƙwalwar GPU ta hanyar tattara gradients akan ƙananan ƙananan batches da yawa kafin haɓakawa…
Ya gama karantawa? Tabbatar da shi.
Check what you learned with a topic quiz, then explore our structured courses or work toward a certificate. Every guide stays free to read.