Iyini i-Edge AI?

I-Edge AI iphusha ubuhlakani ezindaweni lapho idatha izalwa khona. Kuzwakala kumnandi, kodwa umqondo oyinhloko ulula: yenza ukucabanga eduze kwenzwa ukuze imiphumela ibonakale manje, hhayi kamuva. Uthola isivinini, ukwethembeka, kanye nendaba yobumfihlo ehloniphekile ngaphandle kokuthi ifu ligade izingane zonke izinqumo. Masiyikhiphe izinqamuleli kanye nezimfuno eziseceleni ezifakiwe. 😅

Izindatshana ongathanda ukuzifunda ngemva kwalesi:

🔗 Iyini i-AI ekhiqizayo
Incazelo ecacile ye-AI ekhiqizayo, ukuthi isebenza kanjani, nokusetshenziswa okungokoqobo.

🔗 Iyini i-AI ye-agent
Ukubuka konke kwe-AI ye-agent, ukuziphatha okuzimele, namaphethini wohlelo lokusebenza lomhlaba wangempela.

🔗 Iyini i-AI scalability
Funda ukuthi ungakala kanjani amasistimu e-AI ngendlela ethembekile, ephumelelayo, futhi engabizi kakhulu.

🔗 Luyini uhlaka lwesoftware ye-AI
Ukuhlukaniswa kwezinhlaka zesoftware ye-AI, izinzuzo zezakhiwo, nezisekelo zokuqalisa.

Iyini i-Edge AI? Incazelo esheshayo 🧭

I-Edge AI iwumkhuba wokusebenzisa amamodeli okufunda omshini aqeqeshiwe ngokuqondile noma eduze kwamadivayisi aqoqa idatha-amafoni, amakhamera, amarobhothi, izimoto, okugqokekayo, izilawuli zezimboni, ukusho lokho. Esikhundleni sokuthumela idatha eluhlaza kumaseva akude ukuze ihlaziywe, idivayisi icubungula okokufaka endaweni futhi ithumele kuphela izifinyezo noma lutho nhlobo. Uhambo oluncane lokuya nokubuya, ukunensa kancane, ukulawula okwengeziwe. Uma ufuna isichazi esihlanzekile, esingathathi hlangothi somthengisi, qala lapha. [1]

Yini eyenza i-Edge AI ibe wusizo ngempela? 🌟

• Ukubambezeleka okuphansi - izinqumo zenzeka kudivayisi, ngakho-ke izimpendulo zizwakala zishesha emisebenzini yombono efana nokutholwa kwento, ukubonwa kwegama lokuvuka, noma izexwayiso ezingaqondakali. [1]

• Ubumfihlo ngendawo - idatha ebucayi ingahlala kudivayisi, inciphise ukuchayeka futhi isize ngezingxoxo zokunciphisa idatha. [1]

• Ukonga umkhawulokudonsa - thumela izici noma imicimbi esikhundleni sokusakazwa okungahluziwe. [1]

• Ukuqina - kusebenza ngesikhathi sokuxhuma okudwetshiwe.

• Ukulawula izindleko - imijikelezo yokubala yamafu embalwa kanye nokuphuma okuphansi.

• Ukuqwashisa ngomongo - idivayisi "izwa" indawo ezungezile futhi ijwayelane nezimo.

I-anecdote esheshayo: umshayeli wendiza othengisayo ushintshe ukulayishwa kwekhamera okungashintshi ukuze kuhlelwe ukuhlukaniswa kwento okukudivayisi komuntu futhi waphusha ukubala kwehora kuphela neziqeshana ezihlukile. Umphumela: izexwayiso ezingaphansi kuka-200 ms onqenqemeni lweshalofu kanye no-~90% zehla kuthrafikhi ekhuphukayo-ngaphandle kokushintsha izinkontileka ze-WAN zesitolo. (Indlela: ukucatshangelwa kwendawo, ukuhlanganisa imicimbi, okudidayo kuphela.)

I-Edge AI vs cloud AI - umehluko osheshayo 🥊

• Lapho kubalwa khona : onqenqemeni = kudivayisi/eduze kwedivayisi; ifu = izikhungo zedatha ezikude.

• Ukubambezeleka : onqenqemeni ≈ isikhathi sangempela; ifu linohambo oluya nokubuya.

• Ukunyakaza kwedatha : izihlungi zonqenqema / zicindezela kuqala; ifu lithanda ukulayisha okuthembekile.

• Ukuthembeka : i-edge iqhubeka isebenza ungaxhunyiwe ku-inthanethi; ifu lidinga uxhumano.

• Ukubusa : i-edge isekela ukuncishiswa kwedatha; ifu libeka phakathi ukwengamela. [1]

Akuyona noma-noma. Amasistimu ahlakaniphile ahlanganisa kokubili: izinqumo ezisheshayo endaweni, izibalo ezijulile nokufunda kwemikhumbi phakathi nendawo. Impendulo ye-hybrid iyadina-futhi ilungile.

I-Edge AI empeleni isebenza kanjani ngaphansi kwe-hood 🧩

1. Izinzwa zithwebula amasiginali angaphekiwe-ozimele bomsindo, amaphikseli ekhamera, ukuthepha kwe-IMU, ukulandelelwa kokudlidliza.

2. Ukucubungula ngaphambilini kulungisa kabusha lawo masiginali abe izici ezifanele amamodeli.

3. Isikhathi sokusebenza esicatshangelwayo sisebenzisa imodeli ehlangene kudivayisi kusetshenziswa izisheshisi uma sitholakala.

4. I-Postprocessing ishintsha okuphumayo kube imicimbi, amalebula, noma izenzo zokulawula.

5. I-Telemetry ilayisha kuphela okuwusizo: izifinyezo, okudidayo, noma impendulo yezikhathi ezithile.

Izikhathi zokusebenza ezikudivayisi ozozibona endle zifaka phakathi i-LiteRT (ngaphambilini eyayaziwa ngokuthi i-TensorFlow Lite), i-ONNX Runtime , ne-Intel's OpenVINO . Lawa maketango amathuluzi aminyanisa okuphumayo okuvela kubhajethi yamandla aqinile/yenkumbulo ngamaqhinga anjengokwenza amanani kanye nokuhlanganiswa komsebenzisi. Uma uthanda amantongomane namabhawodi, amadokhumenti awo aqinile. [3][4]

Lapho ivela khona - izimo zokusetshenziswa kwangempela ongazikhomba 🧯🚗🏭

• Umbono onqenqemeni : amakhamera ensimbi yomnyango (abantu vs izilwane ezifuywayo), ukuskena ishalofu kwezentengiso, ama-drones abona amaphutha.

• Umsindo kudivayisi : amagama okuvuka, ukubizela, ukutholwa kokuvuzayo ezitshalweni.

• I-IoT Yezimboni : amamotho namaphampu aqashwe ukuze kutholakale okungaqondakali kokudlidliza ngaphambi kokwehluleka.

• Izimoto : ukuqapha abashayeli, ukutholwa komzila, ukupaka kusiza-umzuzwana omncane noma ukuqhuma.

• Ukunakekelwa kwezempilo : okugqokekayo kuhlaba umkhosi ama-arrhythmias endaweni; vumelanisa izifinyezo kamuva.

• Ama-Smartphones : ukuthuthukiswa kwesithombe, ukutholwa kocingo ogaxekile, “ifoni yami ikwenze kanjani lokho ingaxhunyiwe ku-inthanethi” izikhathi.

Ukuze uthole izincazelo ezisemthethweni (kanye nenkulumo yomzala ethi “inkungu iqhudelana nomphetho), bona imodeli yomqondo ye-NIST. [2]

I-hardware eyenza kube lula 🔌

Izinkundla ezimbalwa zihlolwa amagama kakhulu:

• I-NVIDIA Jetson - amamojula anamandla e-GPU amarobhothi/amakhamera-Swiss-Army-knife vibes e-AI eshumekiwe.

• I-Google Edge TPU + LiteRT - inkomba eyinombolo ephelele kanye nesikhathi sokusebenza esihlelekile samaphrojekthi anamandla aphansi kakhulu. [3]

• I-Apple Neural Engine (ANE) - i-ML eqinile kudivayisi ye-iPhone, i-iPad, ne-Mac; I-Apple ishicilele umsebenzi osebenzayo wokuthumela ama-transformer ngempumelelo ku-ANE. [5]

• Ama-Intel CPUs/iGPUs/NPUs ane-OpenVINO - “bhala kanye, sebenzisa noma yikuphi” kuyo yonke i-Intel hardware; amaphasi okuthuthukisa awusizo.

• I-ONNX Runtime yonke indawo - isikhathi sokusebenza esimaphakathi esinabahlinzeki bokusebenzisa abaxhumekayo kuwo wonke amafoni, ama-PC, namasango. [4]

Ingabe uwadinga wonke? Akunjalo Empeleni. Khetha indlela eyodwa enamandla elingana nomkhumbi wakho bese unamathela kuyo-i-churn isitha samaqembu ashumekiwe.

Isitaki sesofthiwe - uhambo olufushane 🧰

• Ukucindezelwa kwemodeli : i-quantization (imvamisa ukuya ku-int8), ukuthena, ukucwiliswa kwe-distillation.

• Ukusheshiswa kwezinga lomsebenzisi : ama-kernel aqondiswe ku-silicon yakho.

• Isikhathi sokusebenza : LiteRT, ONNX Runtime, OpenVINO. [3][4]

• Ama-wrappers okuthunyelwa : iziqukathi/izinqwaba zohlelo lokusebenza; ngezinye izikhathi microservices on amasango.

• Ama-MLOps onqenqema : Izibuyekezo zemodeli ye-OTA, ukukhishwa kwe-A/B, amaluphu e-telemetry.

• Izilawuli zobumfihlo nokuphepha : ukubethela okukudivayisi, ibhuthi evikelekile, ubufakazi, ama-enclaves.

I-Mini-case: ithimba elihlolayo likhiphe umtshina we-heavyweight waba imodeli yomfundi we-LiteRT, lase lihlanganisa i-NMS kudivayisi. Isikhathi sendiza sithuthukisiwe ~ 15% sibonga umdwebo wekhompyutha ophansi; layisha ivolumu ngokuncishiswa kozimele abahlukile. (Indlela: ukuthwebula idathasethi esizeni, ukulinganisa kwangemuva kwenani, imodi yesithunzi A/B ngaphambi kokukhishwa okugcwele.)

Ithebula lokuqhathanisa - izinketho ezidumile ze-Edge AI 🧪

Inkulumo yangempela: leli thebula linombono futhi lingcolile kancane-njengomhlaba wangempela.

Ungayikhetha kanjani indlela ye-Edge AI - isihlahla sesinqumo esincane 🌳

• Isikhathi sangempela esinzima impilo yakho? Qala ngama-accelerator + amamodeli alinganiselwe.

• Izinhlobo eziningi zedivayisi? Thanda isikhathi sokusebenza se-ONNX noma i-OpenVINO ukuze iphatheke. [4]

• Ukuthumela uhlelo lokusebenza lweselula? I-LiteRT iyindlela yokumelana okuncane. [3]

• Amarobhothi noma izibalo zekhamera? I-Jetson's GPU-friendly ops yonga isikhathi.

• Ukuma kobumfihlo okuqinile? Gcina idatha isendaweni, bhala ngemfihlo lapho uphumule, ukuhlanganiswa kwelogi hhayi ozimele abaluhlaza.

• Iqembu elincane? Gwema amaketanga amathuluzi angavamile-okuyisicefe kuhle.

• Amamodeli azoshintsha kaningi? Hlela i-OTA ne-telemetry kusukela ngosuku lokuqala.

Izingozi, imikhawulo, namabhithi ayisicefe-kodwa-abalulekile 🧯

• Imodeli yokukhukhuleka - izindawo ziyashintsha; qapha ukusatshalaliswa, sebenzisa amamodi ethunzi, ziqeqeshe kabusha ngezikhathi ezithile.

• Bala usilingi - inkumbulo eqinile/amandla aphoqelela amamodeli amancane noma ukunemba okukhululekile.

• Ukuphepha - thatha ukufinyelela ngokomzimba; sebenzisa i-boot evikelekile, ama-artifacts asayiniwe, ukufakazela, amasevisi anelungelo elincane.

• Ukuphathwa kwedatha - ukucubungula kwendawo kuyasiza, kodwa usadinga imvume, ukugcinwa, kanye ne-telemetry ebanzi.

• Ama-Fleet ops - amadivaysi awaxhunyiwe ku-inthanethi ngezikhathi ezimbi kakhulu; klama izibuyekezo ezihlehlisiwe kanye nokulayisha okuqhutshekwa nakho.

• Ingxube yethalente - eshumekiwe + ML + DevOps iyiqembu le-motley; ukuwela isitimela kusenesikhathi.

Umdwebo womgwaqo osebenzayo wokuthumela okuthile okuwusizo 🗺️

1. Khetha ikesi elilodwa lokusetshenziswa elinokutholwa kokonakala kwenani elilinganisekayo ku-Line 3, vusa izwi kusipika esihlakaniphile, njll.

2. Qoqa isethi yedatha ehlelekile ebonisa indawo okuqondiwe kuyo; faka umsindo ukufanisa iqiniso.

3. I-Prototype kukhithi ye-dev eduze nehadiwe yokukhiqiza.

4. Cindezela imodeli nge-quantization/ukuthena; linganisa ukulahleka kokunemba ngokwethembeka. [3]

5. Goqa okucatshangelwayo nge-API ehlanzekile ene-backpressure kanye nezinja ezilindile-ngoba amadivayisi alenga ngo-2 ekuseni

6. I-telemetry yedizayini ehlonipha ubumfihlo: ukubala kokuthumela, ama-histogram, izici ezikhishwe onqenqemeni.

7. Qinisa ukuphepha : okuhamba ngakubili okusayiniwe, ibhuthi evikelekile, izinsiza ezincane zivuliwe.

8. Hlela i-OTA : ukukhishwa okunyakazayo, ama-canaries, ukubuyisela emuva ngokushesha.

9. Umshayeli wendiza ekhoneni elibi okokuqala-uma isinda lapho, izosinda noma yikuphi.

10. Isikali ngebhuku lokudlala : uzowangeza kanjani amamodeli, uzungezisa okhiye, gcina kungobo yomlando idatha-ukuze iphrojekthi engu-#2 ayiyona isiphithiphithi.

Imibuzo Evame Ukubuzwa - izimpendulo ezimfushane kokuthi Yini i-Edge AI curiosities ❓

Ingabe i-Edge AI isebenzisa imodeli encane kukhompyutha encane?
Ikakhulukazi, yebo-kodwa ubukhulu akuyona yonke indaba. Kuphinde futhi kumayelana nesabelomali sokubambezeleka, izithembiso zobumfihlo, kanye nokuhlela amadivayisi amaningi asebenza endaweni kodwa afunda emhlabeni jikelele. [1]

Ngingakwazi ukuqeqesha onqenqemeni futhi?
Ukuqeqeshwa okungasindi kudivayisi/ukwenza kube ngokwakho kukhona; ukuqeqeshwa okunzima kakhulu kusasebenza phakathi nendawo. I-ONNX Runtime imadokhumenti ongakhetha kukho kokuqeqeshwa okukudivayisi uma ungumuntu omusha. [4]

Iyini i-Edge AI vs inkungu computing?
Inkungu nomphetho kubazala. Zombili ziletha ikhompuyutha eduze nemithombo yedatha, ngezinye izikhathi ngamasango aseduze. Ukuze uthole izincazelo ezisemthethweni nomongo, bona i-NIST. [2]

Ingabe i-Edge AI ihlala ithuthukisa ubumfihlo?
Kuyasiza-kodwa akuwona umlingo. Usadinga ukuncishiswa, izindlela zokubuyekeza ezivikelekile, nokungena ngokucophelela. Phatha ubumfihlo njengomkhuba, hhayi ibhokisi lokuthikha.

Ukuntywila okujulile ungase ufunde 📚

1) Ukwenza imodeli okungonakalisi ukunemba

Ukulinganisa amanani kunganciphisa inkumbulo futhi kusheshise ukusebenza, kodwa ukulinganisa ngedatha emele noma imodeli ingase ibone izingwejeje lapho kukhona amakhoni wethrafikhi. Uthisha we-distillation oqondisa umfundi omncane-ngokuvamile ugcina i-semantics. [3]

2) I-Edge inference runtimes ekusebenzeni

Umhumushi we-LiteRT uyinkumbulo engaguquki ngamabomu ngesikhathi sokusebenza. I-ONNX Runtime ixhuma kuma-accelerator ahlukene ngokusebenzisa abahlinzeki bokubulala. Futhi ayikho inhlamvu yesiliva; zombili izando eziqinile. [3][4]

3) Ukuqina endle

Ukushisa, uthuli, amandla axegayo, i-slapdash Wi-Fi: yakha izinja eziqapha kabusha amapayipi, izinqumo zenqolobane, futhi zivumelanise uma inethiwekhi ibuya. Akunabukhazikhazi kunokunakwa-kubaluleke kakhulu nokho.

Ibinzana ozoliphinda emihlanganweni - What is Edge AI 🗣️

I-Edge AI isondeza ubuhlakani kudatha ukuze ihlangabezane nezingqinamba ezisebenzayo zokubambezeleka, ubumfihlo, umkhawulokudonsa, nokuthembeka. Umlingo awuyona into eyodwa noma uhlaka-ukhetha ngobuhlakani ukuthi yini okumele uyibale kuphi.

Amazwi Okugcina - Yinde Kakhulu, Angizange Ngiyifunde 🧵

I-Edge AI isebenzisa amamodeli eduze kwedatha ukuze imikhiqizo izizwe ishesha, iyimfihlo, futhi iqinile. Uzohlanganisa okucatshangelwayo kwasendaweni nokugadwa kwamafu ukuze uthole okungcono kakhulu kuyo yomibili imihlaba. Khetha isikhathi sokusebenza esifana namadivayisi akho, ncika kuma-accelerator uma ukwazi, gcina amamodeli ecocekile ngokuminyanisa, futhi uklame imisebenzi yemikhumbi efana nomsebenzi wakho incike kukho-ngoba, kungenzeka. Uma othile ebuza ukuthi Iyini i-Edge AI , yithi: izinqumo ezihlakaniphile, ezenziwe endaweni, ngesikhathi. Bese umomotheka bese ushintsha isihloko sibe amabhethri. 🔋🙂

Izithenjwa

1. I-IBM - Iyini i-Edge AI? (incazelo, izinzuzo).
   https://www.ibm.com/think/topics/edge-ai

2. I-NIST - SP 500-325: Imodeli Yomqondo Yekhompyutha Yenkungu (umongo osemthethweni wenkungu/umphetho).
   https://csrc.nist.gov/pubs/sp/500/325/final

3. I-Google AI Edge - LiteRT (ngaphambilini eyayaziwa nge-TensorFlow Lite) (isikhathi sokusebenza, ukulinganisa, ukufuduka).
   https://ai.google.dev/edge/litert

4. I-ONNX Runtime - Ukuqeqeshwa Okukudivayisi (isikhathi sokusebenza esiphathwayo + ukuqeqeshwa kumadivayisi asemaphethelweni).
   https://onnxruntime.ai/docs/get-started/training-on-device.html

5. I-Apple Machine Learning Research - Ithumela Ama-Transformers ku-Apple Neural Engine (amanothi e-ANE ukusebenza kahle).
   https://machinelearning.apple.com/research/neural-engine-transformers

Thola i-AI yakamuva esitolo esisemthethweni somsizi we-AI

Mayelana NATHI