01
I-AI Foundations
Qonda ukuthi iyini i-AI, ukuthi amasistimu afunda kanjani, lapho ehluleka khona, kanye nendlela yokwahlulela izimangalo ngaphandle kokukhohlisa.
Umtapo wezincwadi we-AI wamahhala
Okuyisisekelo abaqondisiMahhala phakade.
84 imihlahlandlela yesiNgisi esicacile, izindlela zokufunda ezihlelekile, nomtapo wolwazi ovulekile — wakhiwe inhlangano engenzi nzuzo ye-501(c)(3) ezimele ukuze noma ubani aqonde i-AI yesimanje.
84Iziqondiso zamahhala
1Amathrekhi esihloko
~2 minNgomhlahlandlela
~3hIsikhathi sokufunda
Qala lapha
Ezinhlanu izifundo ezisekelwe emiphumeleni
Isifundo ngasinye sihlanganisa imiphumela esobala, amakhono afakwe kumephu, imisebenzi yokuzilolonga, kanye netshe eliyinhloko elisetshenzisiwe.
02
Umsebenzisi we-AI onesibophezelo
Sebenzisa i-AI ngendlela ekhiqizayo kuyilapho uvikela ubumfihlo, ubheka imiphumela, futhi ulondoloza ukuziphendulela komuntu.
03
I-AI emsebenzini
Linganisa izimo zokusetshenziswa kwendawo yokusebenza, sebenzisa abashayeli bezindiza abaphephile, kala inani, futhi uxhumane nezinguquko ngokuzibophezela.
04
Inqubomgomo ye-AI Nomphakathi
Hlaziya izinhlelo ze-AI ngokusebenzisa amalungelo, ukulingana, ukubusa, ukuphepha, kanye nemiphumela yenzuzo yomphakathi.
05
Ukwakha nge-AI Systems
Qonda amamodeli olimi, ukubuyisa, abasebenzeli, ukuhlola, izindleko, nokuvikela ukusetshenziswa ngokuklama kwesistimu okusebenzayo.
Amathrekhi esihloko
Phequlula ngethrekhi
Gxumela endaweni oyikhathalelayo. Wonke amathrekhi anemihlahlandlela eminingi yesiNgisi esilula.
OkuyisisekeloImiqondo eyinhloko: ukuthi i-AI isebenza kanjani ezingeni eliphezulu.84 abaqondisi Ulimi lwe-AIAma-LLM, i-NLP, i-ChatGPT, ukwaziswa, nokuqonda umbhalo.155 abaqondisi I-AI ebonakalayoUkwakhiwa kwesithombe, umbono wekhompyutha, ividiyo, kanye nomklamo.133 abaqondisi Umsindo we-AIIzwi, umculo, i-podcasting, kanye ne-AI yokuqala yomsindo.117 abaqondisi IzinkampaniAmaphrofayili we-OpenAI, Anthropic, Google, Meta, nokunye.121 abaqondisi Izinhlelo zokusebenzaIvela kanjani i-AI ekubhaleni amakhodi, usesho, ama-ejenti, nempilo yansuku zonke.111 abaqondisi IzimboniI-AI kwezokunakekelwa kwempilo, ezezimali, imfundo, amandla, nokuningi.91 abaqondisi UbuchwephesheAma-chips, ukulungisa kahle, i-RAG, ama-vector, nengqalasizinda ye-AI.177 abaqondisi UmphakathiUkuchema, ubumfihlo, i-copyright, ukuphepha, nekusasa le-AI.30 abaqondisi
Umtapo wolwazi ogcwele
Zonke iziqondiso
84 kwe 1019 imihlahlandlela ebonisiwe. Hlunga ngethrekhi noma sesha ngenhla.
Okuyisisekelo
Ukuzishuna Kahle Ukuzidlalela
Ukuzishuna kahle kuthuthukisa imodeli ngokuyenza iqhudelane noma ifunde emiphumeleni yayo edlule, ikhiqize isignali yayo yokuqeqeshwa.
OkuyisisekeloUkuqeqeshwa Kwesikhathi Sokuhlola
Ukuqeqeshwa kwesikhathi sokuhlola (TTT) kuvumela imodeli ukuthi iqhubeke nokufunda kulokho okufakwayo okusha ngesikhathi yenza isibikezelo, esikhundleni sokuhlala iqhwa ngemva kokuqeqeshwa.
OkuyisisekeloGrokking futhi Ukulibaziseka Okujwayelekile
I-Grokking yinto emangazayo lapho inethiwekhi ye-neural iqala ngekhanda idatha yayo yokuqeqeshwa, ihlala endaweni ecishe ibe ngu-zero ukunemba kokuqinisekisa isikhathi eside, bese...
OkuyisisekeloI-Overfitting and Underfitting
I-overfitting yilapho imodeli ibamba ngekhanda idatha yayo yokuqeqeshwa futhi yehluleka ezibonelweni ezintsha; underfitting yilapho kulula kakhulu ukuthwebula iphethini yangempela.
OkuyisisekeloUkwenziwa njalo
I-Regularization iqoqo lamasu acindezela ngamabomu imodeli ukuze ihlanganise idatha entsha esikhundleni sokubamba ngekhanda isethi yokuqeqeshwa.
OkuyisisekeloI-Backpropagation
I-Backpropagation i-algorithm evumela ukuthi inethiwekhi ye-neural ifunde emaphutheni ayo ngokubala kahle ukuthi isisindo ngasinye sibe nesandla esingakanani ephutheni.
OkuyisisekeloUkwehla kweGradient
Ukwehla kwegradient kuyindlela yokuthuthukisa empeleni ehambisa izisindo zemodeli yehle umqansi iye ephutheni eliphansi, isinyathelo esisodwa esincane ngesikhathi.
OkuyisisekeloUkulahlekelwa Imisebenzi
Umsebenzi wokulahlekelwa inombolo eyodwa etshela imodeli ukuthi izibikezelo zayo zingalungile kangakanani, ukuguqula umgomo ongacacile ube okuthile okungathuthukisa izibalo.
OkuyisisekeloImisebenzi Yokuqalisa
Imisebenzi yokuvula ingamasango amancane angewona umugqa ngaphakathi kwe-neuron ngayinye avumela amanethiwekhi e-neural afunde amaphethini ayinkimbinkimbi, agobile esikhundleni semigqa eqondile nje.
OkuyisisekeloI-Convolutional Neural Networks
I-Convolutional Neural Networks (CNNs) iyisakhiwo samahhashi sokuqonda izithombe.
OkuyisisekeloAmanethiwekhi E-Neural Ajwayelekile
I-Recurrent Neural Networks (RNNs) yakhelwe ukuphatha ukulandelana njengombhalo, inkulumo, nochungechunge lwesikhathi.
OkuyisisekeloAmanethiwekhi Akhiqizayo Aphikisanayo
I-Generative Adversarial Networks (GANs) idala idatha entsha engokoqobo ngokuhlanganisa amanethiwekhi amabili e-neural ngokumelene nawo emqhudelwaneni.
Uqedile ukufunda? Ake usikhombise sibone.
Hlola okufundile ngombuzo wesihloko, bese uhlola izifundo zethu ezihlelekile noma usebenzela ukuthola isitifiketi. Wonke umhlahlandlela uhlala ukhululekile ukufunda.