{"id":56370,"date":"2020-02-11T00:00:00","date_gmt":"2020-02-10T21:00:00","guid":{"rendered":"https:\/\/prohoster.info\/blog\/blog_prohoster\/kak-energetik-izuchal-nejroseti-i-obzor-na-besplatnyj-kurs-udacity-intro-to-tensorflow-for-deep-learning"},"modified":"2020-02-18T14:04:38","modified_gmt":"2020-02-18T11:04:38","slug":"kak-energetik-izuchal-nejroseti-i-obzor-na-besplatnyj-kurs-udacity-intro-to-tensorflow-for-deep-learning","status":"publish","type":"post","link":"https:\/\/prohoster.info\/ro\/blog\/news\/kak-energetik-izuchal-nejroseti-i-obzor-na-besplatnyj-kurs-udacity-intro-to-tensorflow-for-deep-learning","title":{"rendered":"Cum un inginer \u00een energetic\u0103 a studiat re\u021bele neuronale \u0219i recenzia unui curs gratuit \u201eUdacity: Introducere \u00een TensorFlow pentru \u00cenv\u0103\u021bare Profund\u0103\u201d","gt_translate_keys":[{"key":"rendered","format":"text"}]},"content":{"rendered":"<p>\u00cen toat\u0103 con\u0219tientizarea mea, am fost electrician (nu, acum nu vorbesc despre o b\u0103utura cu propriet\u0103\u021bi discutabile). <\/p>\n<p>Nu m-am interesat prea mult de lumea tehnologiilor informa\u021biei, iar \u0219i matricele cred c\u0103 greu le-a\u0219 putea \u00eenmul\u021bi pe o foaie de h\u00e2rtie. \u0218i nu mi-a fost niciodat\u0103 necesar, pentru a \u00een\u021belege pu\u021bin din specificul muncii mele, pot \u00eemp\u0103rt\u0103\u0219i o poveste minunat\u0103. Odat\u0103 am cerut colegilor mei s\u0103 fac\u0103 o lucrare \u00een Excel \u2013 o tabel\u0103, a trecut jum\u0103tate din ziua de lucru, m\u0103 apropii de ei, iar ei st\u0103teau \u0219i sumau datele pe un calculator, da- da, pe un calculator obi\u0219nuit, cu butoane negre. Deci, despre ce re\u021bele neuronale ar putea fi vorba dup\u0103 aceasta?\u2026 Prin urmare, nu am avut niciodat\u0103 premise speciale pentru a p\u0103trunde \u00een lumea IT. Dar, cum se spune, \u201ebine este acolo unde nu suntem\u201d, prietenii mei m-au bombardat cu povestiri despre realitatea augmentat\u0103, despre re\u021bele neuronale, despre limbaje de programare (\u00een principal despre Python).<\/p>\n<p>Pe h\u00e2rtie p\u0103rea destul de simplu, a\u0219a c\u0103 am decis de ce s\u0103 nu st\u0103p\u00e2nesc aceast\u0103 art\u0103 magic\u0103 pentru a o aplica \u00een domeniul meu de activitate.<\/p>\n<p>\u00cen acest articol voi omite \u00eencerc\u0103rile mele de a \u00eenv\u0103\u021ba bazele Python \u0219i voi \u00eemp\u0103rt\u0103\u0219i cu voi impresiile mele despre cursul gratuit de TensorFlow de la Udacity.<\/p>\n<p><img decoding=\"async\" alt=\"Cum un inginer \u00een energetic\u0103 a studiat re\u021bele neuronale \u0219i recenzia unui curs gratuit \u201eUdacity: Introducere \u00een TensorFlow pentru \u00cenv\u0103\u021bare Profund\u0103\u201d\" src=\"\/wp-content\/uploads\/2020\/02\/d8955ee8fd84fe551521a7675f425073.jpg\" style=\"display:block;margin: 0 auto;\" \/><br \/>\n<noindex><a rel=\"nofollow\" name=\"habracut\"><\/a><\/noindex><\/p>\n<h2> Introducere<\/h2>\n<p>\n\u00cen primul r\u00e2nd, este important de men\u021bionat c\u0103 dup\u0103 11 ani \u00een domeniul energetic, c\u00e2nd \u0219tii \u0219i po\u021bi face totul \u0219i chiar pu\u021bin mai mult (\u00een cadrul responsabilit\u0103\u021bilor tale), \u00eenv\u0103\u021barea de lucruri complet noi \u2013 pe de o parte, provoac\u0103 un entuziasm puternic, dar pe de alt\u0103 parte \u2013 se transform\u0103 \u00eentr-o durere fizic\u0103 a \u201eroti\u021belor din cap\u201d.<\/p>\n<p>\u00cen continuare, nu \u00een\u021beleg complet toate conceptele de baz\u0103 ale program\u0103rii \u0219i \u00eenv\u0103\u021b\u0103rii automate, a\u0219a c\u0103 nu ar trebui s\u0103 m\u0103 judeci strict. Sper c\u0103 articolul meu va fi interesant \u0219i util pentru cei ca mine \u2013 \u00eendep\u0103rta\u021bi de dezvoltarea software.<\/p>\n<p>\u00cenainte de a trece la review-ul cursului, voi spune c\u0103 pentru a-l studia este necesar\u0103 cel pu\u021bin o cuno\u0219tin\u021b\u0103 minim\u0103 de Python. Po\u021bi citi c\u00e2teva c\u0103r\u021bi pentru \u00eencep\u0103tori (eu am \u00eenceput s\u0103 urmez un curs pe Stepic, dar nu l-am terminat \u00eenc\u0103). <\/p>\n<p>\u00cen cursul de TensorFlow nu vor fi structuri complexe, dar va fi necesar s\u0103 \u00een\u021belegi de ce se import\u0103 bibliotecile, cum se define\u0219te o func\u021bie \u0219i de ce i se introduce ceva.<\/p>\n<h2> De ce TensorFlow \u0219i Udacity? <\/h2>\n<p>\nObiectivul principal al studiului meu a fost dorin\u021ba de a recunoa\u0219te fotografiile elementelor instala\u021biilor electrice cu ajutorul re\u021belelor neuronale. <\/p>\n<p>Am ales TensorFlow pentru c\u0103 am auzit despre el de la prietenii mei. \u0218i, dup\u0103 cum am \u00een\u021beles, acest curs este destul de popular.<\/p>\n<p>Am \u00eencercat s\u0103 \u00eencep studiul cu oficialul <noindex><a rel=\"nofollow\" href=\"https:\/\/www.tensorflow.org\/tutorials\"> tutorial <\/a><\/noindex>.<\/p>\n<p>\u0218i m-am confruntat imediat cu dou\u0103 probleme.<\/p>\n<ul>\n<li>Exist\u0103 multe materiale de \u00eenv\u0103\u021bare, iar acestea sunt haotice. A fost foarte greu pentru mine s\u0103 \u00eemi formez o imagine mai mult sau mai pu\u021bin coerent\u0103 asupra solu\u021biei pentru recunoa\u0219terea imaginilor. <\/li>\n<li>Majoritatea articolelor de care aveam nevoie nu erau traduse \u00een rus\u0103. A\u0219a s-a \u00eent\u00e2mplat c\u0103, \u00een copil\u0103rie, am \u00eenv\u0103\u021bat german\u0103 \u0219i acum, la fel ca mul\u021bi copii sovietici, nu cunosc nici germana, nici engleza. Desigur, \u00een timpul vie\u021bii con\u0219tiente am \u00eencercat s\u0103 st\u0103p\u00e2nesc engleza, dar a ie\u0219it cam a\u0219a cum este \u00een imagine. <\/li>\n<\/ul>\n<p>\n<img decoding=\"async\" alt=\"Cum un inginer \u00een energetic\u0103 a studiat re\u021bele neuronale \u0219i recenzia unui curs gratuit \u201eUdacity: Introducere \u00een TensorFlow pentru \u00cenv\u0103\u021bare Profund\u0103\u201d\" src=\"\/wp-content\/uploads\/2020\/02\/44250d475745cf02ee7126e31f695c3b.jpg\" style=\"display:block;margin: 0 auto;\" \/><br \/>\n<br \/>\nDup\u0103 ce am c\u0103utat mai departe pe site-ul oficial, am g\u0103sit recomand\u0103ri pentru a urma <noindex><a rel=\"nofollow\" href=\"https:\/\/www.tensorflow.org\/resources\/learn-ml\/basics-of-machine-learning\/\"> unul dintre cele dou\u0103 cursuri online<\/a><\/noindex>.<\/p>\n<p>Din c\u00e2te am \u00een\u021beles, cursul de pe Coursera era pl\u0103tit, iar cursul <noindex><a rel=\"nofollow\" href=\"https:\/\/www.udacity.com\/course\/intro-to-tensorflow-for-deep-learning--ud187\"> Udacity: Intro to TensorFlow for Deep Learning<\/a><\/noindex> poate fi urmat \u201ef\u0103r\u0103 plat\u0103, adic\u0103 gratuit\u201d.<\/p>\n<h2> Cuprinsul cursului<\/h2>\n<p>\nCursul const\u0103 din 9 lec\u021bii. <\/p>\n<p>Prima sec\u021biune este introductiv\u0103, acolo se va explica pentru ce este necesar \u00een general.<\/p>\n<p>Lec\u021bia nr. 2 s-a dovedit a fi preferata mea. A fost suficient de simpl\u0103 pentru a fi \u00een\u021beleas\u0103 \u0219i a demonstrat minuni ale \u0219tiin\u021bei. Pe scurt, \u00een aceast\u0103 lec\u021bie, pe l\u00e2ng\u0103 informa\u021biile de baz\u0103 despre re\u021belele neuronale, creatorii demonstreaz\u0103 cum, folosind o re\u021bea neuronal\u0103 unic\u0103, se poate rezolva problema conversiei temperaturii din grade Fahrenheit \u00een grade Celsius.<\/p>\n<p>Este \u00eentr-adev\u0103r un exemplu foarte concludent. \u00cenc\u0103 m\u0103 g\u00e2ndesc cum s\u0103 inventez \u0219i s\u0103 rezolv o problem\u0103 similar\u0103, dar pentru electricitate.<\/p>\n<p>Din p\u0103cate, mai departe m-am \u00eempotmolit, pentru c\u0103 este destul de dificil s\u0103 \u00eenve\u021bi lucruri necunoscute \u00eentr-o limb\u0103 str\u0103in\u0103. M-a salvat faptul c\u0103 am g\u0103sit pe Habr <noindex><a rel=\"nofollow\" href=\"https:\/\/habr.com\/ru\/post\/453482\/\">traducerea acestui curs \u00een limba rus\u0103<\/a><\/noindex>.<\/p>\n<p>Traducerea a fost realizat\u0103 bine, notele Colab au fost de asemenea traduse, a\u0219a c\u0103 am continuat s\u0103 verific at\u00e2t originalul, c\u00e2t \u0219i traducerea.<\/p>\n<p>Lec\u021bia nr. 3 este, de fapt, o reformulare a materialelor tutorialului oficial TensorFlow. \u00cen aceast\u0103 lec\u021bie, \u00eenv\u0103\u021b\u0103m cum s\u0103 clasific\u0103m imaginile cu haine (setul de date Fashion MNIST) folosind o re\u021bea neuronal\u0103 multilayer.<\/p>\n<p>Lectiile cu numerele 4 p\u00e2n\u0103 la 7 sunt, de asemenea, o adaptare a tutorialului. Dar, datorit\u0103 modului \u00een care sunt structurate, nu este necesar s\u0103 te ocupi singur de ordinea studiului. \u00cen aceste lec\u021bii, ne vor vorbi pe scurt despre re\u021bele neuronale super precise, despre cum s\u0103 cre\u0219tem precizia \u00eenv\u0103\u021b\u0103rii \u0219i s\u0103 conserv\u0103m modelul. \u00cen acela\u0219i timp, vom rezolva problema clasific\u0103rii pisicilor \u0219i c\u00e2inilor \u00een imagini.<\/p>\n<p>Lec\u021bia nr. 8 reprezint\u0103, de fapt, un curs separat, av\u00e2nd un alt instructor, iar cursul este destul de cuprinz\u0103tor. Lec\u021bia este dedicat\u0103 seriilor temporale. Deoarece acest subiect nu m\u0103 intereseaz\u0103 \u00eenc\u0103, l-am r\u0103sfoit pe fug\u0103.<\/p>\n<p>Ultima lec\u021bie, nr. 9, este o invita\u021bie de a urma un curs gratuit despre TensorFlow lite.<\/p>\n<h2> Ce mi-a pl\u0103cut \u0219i ce nu mi-a pl\u0103cut<\/h2>\n<p>\nVoi \u00eencepe cu plusurile:<\/p>\n<ul>\n<li> Cursul este gratuit <\/li>\n<li> Cursul este despre TensorFlow 2. Unele manuale pe care le-am v\u0103zut \u0219i unele cursuri online erau despre TensorFlow 1. Nu \u0219tiu c\u00e2t de mare este diferen\u021ba, dar este pl\u0103cut s\u0103 \u00eenve\u021bi versiunea actual\u0103. <\/li>\n<li> Instructorii din videoclipuri nu sunt deranjan\u021bi (de\u0219i \u00een versiunea rus\u0103 citesc nu at\u00e2t de energic ca \u00een original) <\/li>\n<li> Cursul nu dureaz\u0103 mult timp<\/li>\n<li> Cursul nu \u00ee\u021bi d\u0103 o senza\u021bie de triste\u021be \u0219i dezn\u0103dejde. Sarcinile din curs sunt simple \u0219i exist\u0103 \u00eentotdeauna o sugestie sub forma unui Colab cu solu\u021bia corect\u0103, dac\u0103 ceva nu este clar (\u0219i jum\u0103tate dintre sarcini nu au fost clare pentru mine) <\/li>\n<li> Nu trebuie s\u0103 instalezi nimic, toate lucr\u0103rile de laborator ale cursului pot fi realizate \u00een browser<\/li>\n<\/ul>\n<p>\nAcum despre minusuri:<\/p>\n<ul>\n<li> Nu exist\u0103 practic niciun material de control. Nici teste, nici sarcini, nimic pentru a verifica cum am \u00eenv\u0103\u021bat cursul <\/li>\n<li> Nu toate blocnotes-urile au func\u021bionat cum trebuie. Cred c\u0103, \u00een lec\u021bia a treia a cursului original \u00een englez\u0103, Colab a dat o eroare, \u0219i nu am \u0219tiut ce s\u0103 fac cu ea <\/li>\n<li> Este confortabil s\u0103 te ui\u021bi doar pe computer. Poate c\u0103 nu m-am descurcat pe deplin, dar nu am g\u0103sit aplica\u021bia Udacity pe smartphone-ul meu. Iar versiunea mobil\u0103 a site-ului nu este adaptiv\u0103, adic\u0103 aproape \u00eentreaga zon\u0103 de pe ecran este ocupat\u0103 de meniul de navigare, iar pentru a vedea con\u021binutul principal trebuie s\u0103 derulezi spre dreapta dincolo de zona de vizionare. De asemenea, videoclipurile nu pot fi vizionate pe telefon. Pe un ecran de aproximativ 6 inci nu po\u021bi distinge nimic clar.<\/li>\n<li>Unele concepte din curs sunt explicate de mai multe ori, dar aspectele cu adev\u0103rat importante legate de re\u021belele convolu\u021bionale nu sunt adesea discutate. Nu am \u00een\u021beles scopul global al unei p\u0103r\u021bi a exerci\u021biilor, de exemplu, de ce este necesar Max Pooling. <\/li>\n<\/ul>\n<p><\/p>\n<h2> Rezumat<\/h2>\n<p>\nProbabil c\u0103 a\u021bi ghicit c\u0103 minunea nu s-a \u00eent\u00e2mplat. Dup\u0103 parcurgerea acestui curs scurt, nu este posibil s\u0103 \u00een\u021belegem cu adev\u0103rat cum func\u021bioneaz\u0103 re\u021belele neuronale.<\/p>\n<p>Desigur, nu am reu\u0219it singur s\u0103 \u00eemi rezolv problema clasific\u0103rii fotografiilor \u00eentrerup\u0103toarelor \u0219i butoanelor \u00een dispozitivele de distribu\u021bie. <\/p>\n<p>Dar, \u00een ansamblu, cursul este util. Arat\u0103 ce lucruri pot fi realizate cu ajutorul TensorFlow \u0219i \u00een ce direc\u021bie s\u0103 ne \u00eendrept\u0103m mai departe. <\/p>\n<p>Cred c\u0103, pentru \u00eenceput, ar trebui s\u0103 \u00eenv\u0103\u021b bazele Python \u0219i s\u0103 citesc c\u0103r\u021bi \u00een limba rom\u00e2n\u0103 despre cum func\u021bioneaz\u0103 re\u021belele neuronale, dup\u0103 care voi aborda TensorFlow.<\/p>\n<p>\u00cen final, vreau s\u0103 le mul\u021bumesc prietenilor mei pentru c\u0103 m-au \u00eencurajat s\u0103 scriu primul articol pe \"Habr\" \u0219i m-au ajutat s\u0103 \u00eel structurez.<\/p>\n<p>P.S. A\u0219 fi bucuros s\u0103 primesc comentarii \u0219i orice critic\u0103 constructiv\u0103.<br \/>\n<br \/>Sursa: <a content=\"nofollow\" rel=\"nofollow\" href=\"https:\/\/habr.com\/ru\/post\/487950\/\">habr.com<\/a><\/p>","protected":false,"gt_translate_keys":[{"key":"rendered","format":"html"}]},"excerpt":{"rendered":"<p>\u0412\u0441\u044e \u0441\u0432\u043e\u044e \u0441\u043e\u0437\u043d\u0430\u0442\u0435\u043b\u044c\u043d\u0443\u044e \u0436\u0438\u0437\u043d\u044c, \u044f \u0431\u044b\u043b \u044d\u043d\u0435\u0440\u0433\u0435\u0442\u0438\u043a\u043e\u043c (\u043d\u0435\u0442, \u0441\u0435\u0439\u0447\u0430\u0441 \u0440\u0435\u0447\u044c \u043d\u0435 \u0438\u0434\u0435\u0442 \u043e \u043d\u0430\u043f\u0438\u0442\u043a\u0435 \u0441 \u0441\u043e\u043c\u043d\u0438\u0442\u0435\u043b\u044c\u043d\u044b\u043c\u0438 \u0441\u0432\u043e\u0439\u0441\u0442\u0432\u0430\u043c\u0438). \u042f \u043d\u0438\u043a\u043e\u0433\u0434\u0430 \u043e\u0441\u043e\u0431\u043e \u043d\u0435 \u0438\u043d\u0442\u0435\u0440\u0435\u0441\u043e\u0432\u0430\u043b\u0441\u044f \u043c\u0438\u0440\u043e\u043c \u0438\u043d\u0444\u043e\u0440\u043c\u0430\u0446\u0438\u043e\u043d\u043d\u044b\u0445 \u0442\u0435\u0445\u043d\u043e\u043b\u043e\u0433\u0438\u0439, \u0434\u0430 \u0438 \u0434\u0430\u0436\u0435 \u043c\u0430\u0442\u0440\u0438\u0446\u044b \u044f \u0432\u0440\u044f\u0434 \u043b\u0438 \u043d\u0430 \u043b\u0438\u0441\u0442\u043e\u0447\u043a\u0435 \u0441\u043c\u043e\u0433\u0443 \u043f\u0435\u0440\u0435\u043c\u043d\u043e\u0436\u0438\u0442\u044c. \u0414\u0430 \u0438 \u043d\u0435 \u043d\u0443\u0436\u043d\u043e \u043c\u043d\u0435 \u044d\u0442\u043e \u0431\u044b\u043b\u043e \u043d\u0438\u043a\u043e\u0433\u0434\u0430, \u0447\u0442\u043e\u0431\u044b \u0432\u044b \u043f\u043e\u043d\u0438\u043c\u0430\u043b\u0438 \u043d\u0435\u043c\u043d\u043e\u0433\u043e \u043e \u0441\u043f\u0435\u0446\u0438\u0444\u0438\u043a\u0435 \u043c\u043e\u0435\u0439 \u0440\u0430\u0431\u043e\u0442\u044b, \u043c\u043e\u0433\u0443 \u043f\u043e\u0434\u0435\u043b\u0438\u0442\u044c\u0441\u044f \u0437\u0430\u043c\u0435\u0447\u0430\u0442\u0435\u043b\u044c\u043d\u043e\u0439 [&hellip;]<\/p>\n","protected":false,"gt_translate_keys":[{"key":"rendered","format":"html"}]},"author":1,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[702],"tags":[],"class_list":["post-56370","post","type-post","status-publish","format-standard","hentry","category-news"],"aioseo_notices":[],"aioseo_head":"\n\t\t<!-- All in One SEO 5.0.2.1 - aioseo.com -->\n\t<meta name=\"description\" content=\"\u0412\u0441\u044e \u0441\u0432\u043e\u044e \u0441\u043e\u0437\u043d\u0430\u0442\u0435\u043b\u044c\u043d\u0443\u044e \u0436\u0438\u0437\u043d\u044c, \u044f \u0431\u044b\u043b \u044d\u043d\u0435\u0440\u0433\u0435\u0442\u0438\u043a\u043e\u043c (\u043d\u0435\u0442, \u0441\u0435\u0439\u0447\u0430\u0441 \u0440\u0435\u0447\u044c \u043d\u0435 \u0438\u0434\u0435\u0442 \u043e \u043d\u0430\u043f\u0438\u0442\u043a\u0435 \u0441 \u0441\u043e\u043c\u043d\u0438\u0442\u0435\u043b\u044c\u043d\u044b\u043c\u0438 \u0441\u0432\u043e\u0439\u0441\u0442\u0432\u0430\u043c\u0438).\" \/>\n\t<meta name=\"robots\" content=\"max-image-preview:large\" \/>\n\t<meta name=\"author\" content=\"Yuri Gagarin\"\/>\n\t<link rel=\"canonical\" href=\"https:\/\/prohoster.info\/ro\/blog\/news\/kak-energetik-izuchal-nejroseti-i-obzor-na-besplatnyj-kurs-udacity-intro-to-tensorflow-for-deep-learning\" \/>\n\t<meta name=\"generator\" content=\"All in One SEO (AIOSEO) 5.0.2.1\" \/>\n\t\t<meta property=\"og:locale\" content=\"ro_RO\" \/>\n\t\t<meta property=\"og:site_name\" content=\"ProHoster | \u041a\u0443\u043f\u0438\u0442\u044c \u043d\u0430\u0434\u0435\u0436\u043d\u044b\u0439 \u0445\u043e\u0441\u0442\u0438\u043d\u0433 \u0434\u043b\u044f \u0441\u0430\u0439\u0442\u043e\u0432 \u0441 \u0437\u0430\u0449\u0438\u0442\u043e\u0439 \u043e\u0442 DDoS, VPS VDS \u0441\u0435\u0440\u0432\u0435\u0440\u044b\" \/>\n\t\t<meta property=\"og:type\" content=\"article\" \/>\n\t\t<meta property=\"og:title\" content=\"\ud83e\udd47\u041a\u0430\u043a \u044d\u043d\u0435\u0440\u0433\u0435\u0442\u0438\u043a \u0438\u0437\u0443\u0447\u0430\u043b \u043d\u0435\u0439\u0440\u043e\u0441\u0435\u0442\u0438 \u0438 \u043e\u0431\u0437\u043e\u0440 \u043d\u0430 \u0431\u0435\u0441\u043f\u043b\u0430\u0442\u043d\u044b\u0439 \u043a\u0443\u0440\u0441 \u00abUdacity: Intro to TensorFlow for Deep Learning\u00bb | ProHoster\" \/>\n\t\t<meta property=\"og:description\" content=\"\u0412\u0441\u044e \u0441\u0432\u043e\u044e \u0441\u043e\u0437\u043d\u0430\u0442\u0435\u043b\u044c\u043d\u0443\u044e \u0436\u0438\u0437\u043d\u044c, \u044f \u0431\u044b\u043b \u044d\u043d\u0435\u0440\u0433\u0435\u0442\u0438\u043a\u043e\u043c (\u043d\u0435\u0442, \u0441\u0435\u0439\u0447\u0430\u0441 \u0440\u0435\u0447\u044c \u043d\u0435 \u0438\u0434\u0435\u0442 \u043e \u043d\u0430\u043f\u0438\u0442\u043a\u0435 \u0441 \u0441\u043e\u043c\u043d\u0438\u0442\u0435\u043b\u044c\u043d\u044b\u043c\u0438 \u0441\u0432\u043e\u0439\u0441\u0442\u0432\u0430\u043c\u0438).\" \/>\n\t\t<meta property=\"og:url\" content=\"https:\/\/prohoster.info\/ro\/blog\/news\/kak-energetik-izuchal-nejroseti-i-obzor-na-besplatnyj-kurs-udacity-intro-to-tensorflow-for-deep-learning\" \/>\n\t\t<meta property=\"og:image\" content=\"https:\/\/prohoster.info\/wp-content\/uploads\/2021\/11\/logo-350.jpg\" \/>\n\t\t<meta property=\"og:image:secure_url\" content=\"https:\/\/prohoster.info\/wp-content\/uploads\/2021\/11\/logo-350.jpg\" \/>\n\t\t<meta property=\"og:image:width\" content=\"350\" \/>\n\t\t<meta property=\"og:image:height\" content=\"350\" \/>\n\t\t<meta property=\"article:published_time\" content=\"2020-02-10T21:00:00+00:00\" \/>\n\t\t<meta property=\"article:modified_time\" content=\"2020-02-18T11:04:38+00:00\" \/>\n\t\t<meta property=\"article:publisher\" content=\"https:\/\/www.facebook.com\/prohoster\" \/>\n\t\t<meta property=\"article:author\" content=\"https:\/\/www.facebook.com\/prohoster\" \/>\n\t\t<!-- All in One SEO -->\n\n","aioseo_head_json":{"title":"\ud83e\udd47Cum un inginer energetic a studiat re\u021bele neuronale \u0219i recenzia unui curs gratuit \"Udacity: Intro to TensorFlow for Deep Learning\" | ProHoster","description":"\u00cen toat\u0103 con\u0219tientizarea mea, am fost electrician (nu, acum nu vorbesc despre o b\u0103utura cu propriet\u0103\u021bi discutabile).","canonical_url":"https:\/\/prohoster.info\/ro\/blog\/news\/kak-energetik-izuchal-nejroseti-i-obzor-na-besplatnyj-kurs-udacity-intro-to-tensorflow-for-deep-learning","robots":"max-image-preview:large","keywords":"","webmasterTools":{"miscellaneous":""},"schema":null,"og:locale":"ro_RO","og:site_name":"ProHoster | \u041a\u0443\u043f\u0438\u0442\u044c \u043d\u0430\u0434\u0435\u0436\u043d\u044b\u0439 \u0445\u043e\u0441\u0442\u0438\u043d\u0433 \u0434\u043b\u044f \u0441\u0430\u0439\u0442\u043e\u0432 \u0441 \u0437\u0430\u0449\u0438\u0442\u043e\u0439 \u043e\u0442 DDoS, VPS VDS \u0441\u0435\u0440\u0432\u0435\u0440\u044b","og:type":"article","og:title":"\ud83e\udd47\u041a\u0430\u043a \u044d\u043d\u0435\u0440\u0433\u0435\u0442\u0438\u043a \u0438\u0437\u0443\u0447\u0430\u043b \u043d\u0435\u0439\u0440\u043e\u0441\u0435\u0442\u0438 \u0438 \u043e\u0431\u0437\u043e\u0440 \u043d\u0430 \u0431\u0435\u0441\u043f\u043b\u0430\u0442\u043d\u044b\u0439 \u043a\u0443\u0440\u0441 \u00abUdacity: Intro to TensorFlow for Deep Learning\u00bb | ProHoster","og:description":"\u0412\u0441\u044e \u0441\u0432\u043e\u044e \u0441\u043e\u0437\u043d\u0430\u0442\u0435\u043b\u044c\u043d\u0443\u044e \u0436\u0438\u0437\u043d\u044c, \u044f \u0431\u044b\u043b \u044d\u043d\u0435\u0440\u0433\u0435\u0442\u0438\u043a\u043e\u043c (\u043d\u0435\u0442, \u0441\u0435\u0439\u0447\u0430\u0441 \u0440\u0435\u0447\u044c \u043d\u0435 \u0438\u0434\u0435\u0442 \u043e \u043d\u0430\u043f\u0438\u0442\u043a\u0435 \u0441 \u0441\u043e\u043c\u043d\u0438\u0442\u0435\u043b\u044c\u043d\u044b\u043c\u0438 \u0441\u0432\u043e\u0439\u0441\u0442\u0432\u0430\u043c\u0438).","og:url":"https:\/\/prohoster.info\/ro\/blog\/news\/kak-energetik-izuchal-nejroseti-i-obzor-na-besplatnyj-kurs-udacity-intro-to-tensorflow-for-deep-learning","og:image":"https:\/\/prohoster.info\/wp-content\/uploads\/2021\/11\/logo-350.jpg","og:image:secure_url":"https:\/\/prohoster.info\/wp-content\/uploads\/2021\/11\/logo-350.jpg","og:image:width":350,"og:image:height":350,"article:published_time":"2020-02-10T21:00:00+00:00","article:modified_time":"2020-02-18T11:04:38+00:00","article:publisher":"https:\/\/www.facebook.com\/prohoster","article:author":"https:\/\/www.facebook.com\/prohoster"},"aioseo_meta_data":{"post_id":"56370","title":null,"description":null,"keywords":null,"keyphrases":null,"primary_term":null,"canonical_url":null,"og_title":null,"og_description":null,"og_object_type":"default","og_image_type":"default","og_image_url":null,"og_image_width":null,"og_image_height":null,"og_image_custom_url":null,"og_image_custom_fields":null,"og_video":null,"og_custom_url":null,"og_article_section":null,"og_article_tags":null,"twitter_use_og":false,"twitter_card":"default","twitter_image_type":"default","twitter_image_url":null,"twitter_image_custom_url":null,"twitter_image_custom_fields":null,"twitter_title":null,"twitter_description":null,"schema":{"blockGraphs":[],"customGraphs":[],"default":{"data":{"Article":[],"Course":[],"Dataset":[],"FAQPage":[],"Movie":[],"Person":[],"Product":[],"ProductReview":[],"Car":[],"Recipe":[],"Service":[],"SoftwareApplication":[],"WebPage":[]},"graphName":"","isEnabled":true},"graphs":[]},"schema_type":null,"schema_type_options":null,"pillar_content":false,"robots_default":true,"robots_noindex":false,"robots_noarchive":false,"robots_nosnippet":false,"robots_nofollow":false,"robots_noimageindex":false,"robots_noodp":false,"robots_notranslate":false,"robots_max_snippet":null,"robots_max_videopreview":null,"robots_max_imagepreview":"large","priority":null,"frequency":null,"local_seo":null,"seo_analyzer_scan_date":null,"breadcrumb_settings":null,"limit_modified_date":false,"reviewed_by":null,"ai":null,"created":"2021-02-28 19:26:38","updated":"2022-10-07 20:14:09","focus_keyword":null,"additional_keywords":null,"truseo_locale":null},"gt_translate_keys":[{"key":"link","format":"url"}],"_links":{"self":[{"href":"https:\/\/prohoster.info\/ro\/wp-json\/wp\/v2\/posts\/56370","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/prohoster.info\/ro\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/prohoster.info\/ro\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/prohoster.info\/ro\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/prohoster.info\/ro\/wp-json\/wp\/v2\/comments?post=56370"}],"version-history":[{"count":0,"href":"https:\/\/prohoster.info\/ro\/wp-json\/wp\/v2\/posts\/56370\/revisions"}],"wp:attachment":[{"href":"https:\/\/prohoster.info\/ro\/wp-json\/wp\/v2\/media?parent=56370"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/prohoster.info\/ro\/wp-json\/wp\/v2\/categories?post=56370"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/prohoster.info\/ro\/wp-json\/wp\/v2\/tags?post=56370"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}