Umtapo wezincwadi we-AI wamahhala

Umsindo we-AI abaqondisiMahhala phakade.

117 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.

117Iziqondiso zamahhala

1Amathrekhi esihloko

~2 minNgomhlahlandlela

~4hIsikhathi sokufunda

Qala lapha

Ezinhlanu izifundo ezisekelwe emiphumeleni

Isifundo ngasinye sihlanganisa imiphumela esobala, amakhono afakwe kumephu, imisebenzi yokuzilolonga, kanye netshe eliyinhloko elisetshenzisiwe.

I-AI Foundations

Qonda ukuthi iyini i-AI, ukuthi amasistimu afunda kanjani, lapho ehluleka khona, kanye nendlela yokwahlulela izimangalo ngaphandle kokukhohlisa.

~4h ukuqedelaBuka inkambo

Umsebenzisi we-AI onesibophezelo

Sebenzisa i-AI ngendlela ekhiqizayo kuyilapho uvikela ubumfihlo, ubheka imiphumela, futhi ulondoloza ukuziphendulela komuntu.

~5h ukuqedelaBuka inkambo

I-AI emsebenzini

Linganisa izimo zokusetshenziswa kwendawo yokusebenza, sebenzisa abashayeli bezindiza abaphephile, kala inani, futhi uxhumane nezinguquko ngokuzibophezela.

~6h ukuqedelaBuka inkambo

Inqubomgomo ye-AI Nomphakathi

Hlaziya izinhlelo ze-AI ngokusebenzisa amalungelo, ukulingana, ukubusa, ukuphepha, kanye nemiphumela yenzuzo yomphakathi.

~6h ukuqedelaBuka inkambo

Ukwakha nge-AI Systems

Qonda amamodeli olimi, ukubuyisa, abasebenzeli, ukuhlola, izindleko, nokuvikela ukusetshenziswa ngokuklama kwesistimu okusebenzayo.

~8h ukuqedelaBuka inkambo

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

117 kwe 1019 imihlahlandlela ebonisiwe. Hlunga ngethrekhi noma sesha ngenhla.

Umsindo we-AI

I-Beamforming kanye ne-Microphone Arrays

I-Beamforming isebenzisa imibhobho eminingi ukuze ilalele iqonde lapho ikhethiwe, ikhulise umsindo osuka kulokho okuqondiwe kuyilapho icindezela konke okunye.

2 min fundaFunda

Umsindo we-AI

I-Riffusion Spectrogram Diffusion

I-Riffusion iyigebe elihlakaniphile elikhiqiza umculo ngokuphatha umsindo njengesithombe: ishuna kahle imodeli yesithombe eStable Diffusion ukuze ipende ama-spectrogram, bese...

2 min fundaFunda

Umsindo we-AI

I-MusicLM: Amathokheni e-Hierarchical Semantic kanye ne-Acoustic

Funda ukuthi Google i-MusicLM isebenzisa kanjani amathokheni e-hierarchical semantic kanye ne-acoustic, i-SoundStream, ne-MuLan ukuze iguqule ukwaziswa kombhalo kube umculo ohambisanayo.

2 min fundaFunda

Umsindo we-AI

Ukuthuthukisa Inkulumo Yomsindo2

I-Noise2Noise iqhinga lokuqeqesha elivumela imodeli ukuthi ifunde ukususa umsindo ngaphandle kokubona ireferensi ehlanzekile, ngokufunda kumapheya womsindo ohlukile...

2 min fundaFunda

Umsindo we-AI

I-Conv-TasNet Time-Domain Separation

I-Conv-TasNet iyinethiwekhi ye-neural ehlukanisa umsindo oxubile (njengabantu ababili abakhuluma ngesikhathi esisodwa) ngokusebenza ngqo kufomethi yegagasi lomsindo oluhlaza esikhundleni salokho...

2 min fundaFunda

Umsindo we-AI

Ukuhlukaniswa kwe-RNN ye-Dual-Path

I-Dual-Path RNN (DPRNN) iyisakhiwo sokuhlukanisa umsindo esihlukanisa ukulandelana okude kakhulu kwezici zomsindo zibe izingcezu ezifushane ezidlulanayo futhi zizicubungule…

2 min fundaFunda

Umsindo we-AI

Ukwehlukana Komculo Ovulekile-Unmix

I-Open-Unmix (UMX) iyisistimu yokufunda ejulile enomthombo ovulekile ehlukanisa ingoma ibe izingxenye zayo: amazwi, izigubhu, i-bass, nezinye izinsimbi.

2 min fundaFunda

Umsindo we-AI

Ukuqondanisa Kwegama Elinesitembu Sesikhathi

Ukuqondanisa kwegama elihlebayo kukhomba igama ngalinye elilotshiwe ekuqaleni kanye nesikhathi sokugcina emsindweni.

2 min fundaFunda

Umsindo we-AI

Ukumaka Umculo ngama-Transformers

Ukumaka umculo kusebenzisa amamodeli e-transformer ukulalela ingoma nokubikezela amalebula achazayo afana nohlobo, ukuma kwenhliziyo, izinsimbi, kanye ne-tempo.

2 min fundaFunda

Umsindo we-AI

Ukutholwa Kokuqala Kumsindo

Ukutholwa kokuqalisa kuthola izikhathi ezinembile lapho amanothi, amabhithi, noma imisindo iqala kusignali yomsindo.

2 min fundaFunda

Umsindo we-AI

I-MelGAN Generative Vocoder

I-MelGAN iyivoda esekelwe ngokugcwele ye-GAN eshintsha ama-mel-spectrogram abe amaza omsindo angahluziwe ngendlela eyodwa eya phambili esheshayo.

2 min fundaFunda

Umsindo we-AI

I-UnivNet Multi-Resolution Vocoder

I-UnivNet iyivokhoda ye-GAN ehlulelayo ekhiqize umsindo kusetshenziswa ama-spectrogram amaningi enziwe ngekhompyutha ngezinqumo ezihlukene ze-STFT, elola imininingwane yefrikhwensi ephezulu.

2 min fundaFunda

Uqedile ukufunda? Ake usikhombise sibone.

Check what you learned with a topic quiz, then explore our structured courses or work toward a certificate. Every guide stays free to read.

Hlola okufundile Thola isitifiketi Nikela Funda inhloso yethu