{"id":478656,"date":"2023-08-09T09:36:27","date_gmt":"2023-08-09T09:36:27","guid":{"rendered":""},"modified":"2023-09-05T11:17:18","modified_gmt":"2023-09-05T11:17:18","slug":"recurrent-neutral-network","status":"publish","type":"wiki","link":"https:\/\/oneproxy.pro\/vn\/wiki\/recurrent-neutral-network\/","title":{"rendered":"M\u1ea1ng trung t\u00ednh \u0111\u1ecbnh k\u1ef3"},"content":{"rendered":"<p>Th\u00f4ng tin t\u00f3m t\u1eaft v\u1ec1 M\u1ea1ng th\u1ea7n kinh t\u00e1i ph\u00e1t (RNN):<\/p>\n<p>M\u1ea1ng th\u1ea7n kinh t\u00e1i ph\u00e1t (RNN) l\u00e0 m\u1ed9t l\u1edbp m\u1ea1ng th\u1ea7n kinh nh\u00e2n t\u1ea1o \u0111\u01b0\u1ee3c thi\u1ebft k\u1ebf \u0111\u1ec3 nh\u1eadn d\u1ea1ng c\u00e1c m\u1eabu theo chu\u1ed7i d\u1eef li\u1ec7u, ch\u1eb3ng h\u1ea1n nh\u01b0 d\u1eef li\u1ec7u v\u0103n b\u1ea3n, gi\u1ecdng n\u00f3i ho\u1eb7c chu\u1ed7i th\u1eddi gian b\u1eb1ng s\u1ed1. Kh\u00f4ng gi\u1ed1ng nh\u01b0 c\u00e1c m\u1ea1ng n\u01a1-ron truy\u1ec1n th\u1eb3ng, RNN c\u00f3 c\u00e1c k\u1ebft n\u1ed1i t\u1ef1 l\u1eb7p l\u1ea1i, cho ph\u00e9p th\u00f4ng tin t\u1ed3n t\u1ea1i l\u00e2u d\u00e0i v\u00e0 cung c\u1ea5p m\u1ed9t d\u1ea1ng b\u1ed9 nh\u1edb. \u0110i\u1ec1u n\u00e0y l\u00e0m cho RNN ph\u00f9 h\u1ee3p v\u1edbi c\u00e1c nhi\u1ec7m v\u1ee5 trong \u0111\u00f3 \u0111\u1ed9ng l\u1ef1c h\u1ecdc th\u1eddi gian v\u00e0 m\u00f4 h\u00ecnh h\u00f3a tr\u00ecnh t\u1ef1 l\u00e0 quan tr\u1ecdng.<\/p>\n<h2>L\u1ecbch s\u1eed v\u1ec1 ngu\u1ed3n g\u1ed1c c\u1ee7a m\u1ea1ng l\u01b0\u1edbi th\u1ea7n kinh t\u00e1i ph\u00e1t v\u00e0 s\u1ef1 \u0111\u1ec1 c\u1eadp \u0111\u1ea7u ti\u00ean v\u1ec1 n\u00f3<\/h2>\n<p>Kh\u00e1i ni\u1ec7m RNN b\u1eaft ngu\u1ed3n t\u1eeb nh\u1eefng n\u0103m 1980, v\u1edbi nh\u1eefng nghi\u00ean c\u1ee9u ban \u0111\u1ea7u c\u1ee7a c\u00e1c nh\u00e0 nghi\u00ean c\u1ee9u nh\u01b0 David Rumelhart, Geoffrey Hinton v\u00e0 Ronald Williams. H\u1ecd \u0111\u1ec1 xu\u1ea5t c\u00e1c m\u00f4 h\u00ecnh \u0111\u01a1n gi\u1ea3n \u0111\u1ec3 m\u00f4 t\u1ea3 c\u00e1ch m\u1ea1ng l\u01b0\u1edbi th\u1ea7n kinh c\u00f3 th\u1ec3 truy\u1ec1n th\u00f4ng tin theo v\u00f2ng l\u1eb7p, cung c\u1ea5p c\u01a1 ch\u1ebf b\u1ed9 nh\u1edb. Thu\u1eadt to\u00e1n Backpropagation Through Time (BPTT) n\u1ed5i ti\u1ebfng \u0111\u00e3 \u0111\u01b0\u1ee3c ph\u00e1t tri\u1ec3n trong th\u1eddi gian n\u00e0y, tr\u1edf th\u00e0nh m\u1ed9t k\u1ef9 thu\u1eadt \u0111\u00e0o t\u1ea1o c\u01a1 b\u1ea3n cho RNN.<\/p>\n<h2>Th\u00f4ng tin chi ti\u1ebft v\u1ec1 M\u1ea1ng th\u1ea7n kinh t\u00e1i ph\u00e1t<\/h2>\n<p>M\u1ea1ng th\u1ea7n kinh t\u00e1i ph\u00e1t \u0111\u01b0\u1ee3c s\u1eed d\u1ee5ng r\u1ed9ng r\u00e3i cho c\u00e1c nhi\u1ec7m v\u1ee5 kh\u00e1c nhau nh\u01b0 x\u1eed l\u00fd ng\u00f4n ng\u1eef t\u1ef1 nhi\u00ean, nh\u1eadn d\u1ea1ng gi\u1ecdng n\u00f3i v\u00e0 d\u1ef1 b\u00e1o t\u00e0i ch\u00ednh. T\u00ednh n\u0103ng ch\u00ednh gi\u00fap ph\u00e2n bi\u1ec7t RNN v\u1edbi c\u00e1c m\u1ea1ng th\u1ea7n kinh kh\u00e1c l\u00e0 kh\u1ea3 n\u0103ng s\u1eed d\u1ee5ng tr\u1ea1ng th\u00e1i b\u00ean trong (b\u1ed9 nh\u1edb) \u0111\u1ec3 x\u1eed l\u00fd c\u00e1c chu\u1ed7i \u0111\u1ea7u v\u00e0o c\u00f3 \u0111\u1ed9 d\u00e0i thay \u0111\u1ed5i.<\/p>\n<h3>M\u1ea1ng Elman v\u00e0 M\u1ea1ng Jordan<\/h3>\n<p>Hai lo\u1ea1i RNN n\u1ed5i ti\u1ebfng l\u00e0 Elman Networks v\u00e0 Jordan Networks, kh\u00e1c nhau v\u1ec1 k\u1ebft n\u1ed1i ph\u1ea3n h\u1ed3i. M\u1ea1ng Elman c\u00f3 c\u00e1c k\u1ebft n\u1ed1i t\u1eeb l\u1edbp \u1ea9n \u0111\u1ebfn ch\u00ednh ch\u00fang, trong khi M\u1ea1ng Jordan c\u00f3 k\u1ebft n\u1ed1i t\u1eeb l\u1edbp \u0111\u1ea7u ra \u0111\u1ebfn l\u1edbp \u1ea9n.<\/p>\n<h2>C\u1ea5u tr\u00fac b\u00ean trong c\u1ee7a m\u1ea1ng th\u1ea7n kinh t\u00e1i ph\u00e1t<\/h2>\n<p>RNN bao g\u1ed3m c\u00e1c l\u1edbp \u0111\u1ea7u v\u00e0o, l\u1edbp \u1ea9n v\u00e0 l\u1edbp \u0111\u1ea7u ra. \u0110i\u1ec1u l\u00e0m cho ch\u00fang tr\u1edf n\u00ean \u0111\u1ed9c \u0111\u00e1o l\u00e0 k\u1ebft n\u1ed1i \u0111\u1ecbnh k\u1ef3 trong l\u1edbp \u1ea9n. M\u1ed9t c\u1ea5u tr\u00fac \u0111\u01a1n gi\u1ea3n c\u00f3 th\u1ec3 \u0111\u01b0\u1ee3c gi\u1ea3i th\u00edch nh\u01b0 sau:<\/p>\n<ol>\n<li><strong>L\u1edbp \u0111\u1ea7u v\u00e0o<\/strong>: Nh\u1eadn chu\u1ed7i \u0111\u1ea7u v\u00e0o.<\/li>\n<li><strong>L\u1edbp \u1ea9n<\/strong>: X\u1eed l\u00fd c\u00e1c \u0111\u1ea7u v\u00e0o v\u00e0 tr\u1ea1ng th\u00e1i \u1ea9n tr\u01b0\u1edbc \u0111\u00f3, t\u1ea1o ra tr\u1ea1ng th\u00e1i \u1ea9n m\u1edbi.<\/li>\n<li><strong>L\u1edbp \u0111\u1ea7u ra<\/strong>: T\u1ea1o \u0111\u1ea7u ra cu\u1ed1i c\u00f9ng d\u1ef1a tr\u00ean tr\u1ea1ng th\u00e1i \u1ea9n hi\u1ec7n t\u1ea1i.<\/li>\n<\/ol>\n<p>C\u00e1c ch\u1ee9c n\u0103ng k\u00edch ho\u1ea1t kh\u00e1c nhau nh\u01b0 tanh, sigmoid ho\u1eb7c ReLU c\u00f3 th\u1ec3 \u0111\u01b0\u1ee3c \u00e1p d\u1ee5ng trong c\u00e1c l\u1edbp \u1ea9n.<\/p>\n<h2>Ph\u00e2n t\u00edch c\u00e1c t\u00ednh n\u0103ng ch\u00ednh c\u1ee7a m\u1ea1ng th\u1ea7n kinh t\u00e1i ph\u00e1t<\/h2>\n<p>C\u00e1c t\u00ednh n\u0103ng ch\u00ednh bao g\u1ed3m:<\/p>\n<ol>\n<li><strong>X\u1eed l\u00fd tr\u00ecnh t\u1ef1<\/strong>: Kh\u1ea3 n\u0103ng x\u1eed l\u00fd c\u00e1c chu\u1ed7i c\u00f3 \u0111\u1ed9 d\u00e0i thay \u0111\u1ed5i.<\/li>\n<li><strong>K\u00fd \u1ee9c<\/strong>: L\u01b0u tr\u1eef th\u00f4ng tin t\u1eeb c\u00e1c b\u01b0\u1edbc th\u1eddi gian tr\u01b0\u1edbc \u0111\u00f3.<\/li>\n<li><strong>Th\u1eed th\u00e1ch \u0111\u00e0o t\u1ea1o<\/strong>: D\u1ec5 g\u1eb7p ph\u1ea3i c\u00e1c v\u1ea5n \u0111\u1ec1 nh\u01b0 \u0111\u1ed9 d\u1ed1c bi\u1ebfn m\u1ea5t v\u00e0 b\u00f9ng n\u1ed5.<\/li>\n<li><strong>Uy\u1ec3n chuy\u1ec3n<\/strong>: Kh\u1ea3 n\u0103ng \u00e1p d\u1ee5ng cho c\u00e1c nhi\u1ec7m v\u1ee5 kh\u00e1c nhau tr\u00ean c\u00e1c l\u0129nh v\u1ef1c kh\u00e1c nhau.<\/li>\n<\/ol>\n<h2>C\u00e1c lo\u1ea1i m\u1ea1ng th\u1ea7n kinh t\u00e1i ph\u00e1t<\/h2>\n<p>M\u1ed9t s\u1ed1 bi\u1ebfn th\u1ec3 c\u1ee7a RNN t\u1ed3n t\u1ea1i, bao g\u1ed3m:<\/p>\n<table>\n<thead>\n<tr>\n<th>Ki\u1ec3u<\/th>\n<th>S\u1ef1 mi\u00eau t\u1ea3<\/th>\n<\/tr>\n<\/thead>\n<tbody>\n<tr>\n<td>Vani RNN<\/td>\n<td>C\u1ea5u tr\u00fac c\u01a1 b\u1ea3n, c\u00f3 th\u1ec3 g\u1eb7p v\u1ea5n \u0111\u1ec1 v\u1ec1 \u0111\u1ed9 d\u1ed1c bi\u1ebfn m\u1ea5t<\/td>\n<\/tr>\n<tr>\n<td>LSTM (B\u1ed9 nh\u1edb ng\u1eafn h\u1ea1n d\u00e0i)<\/td>\n<td>Gi\u1ea3i quy\u1ebft v\u1ea5n \u0111\u1ec1 bi\u1ebfn m\u1ea5t \u0111\u1ed9 d\u1ed1c v\u1edbi c\u00e1c c\u1ed5ng \u0111\u1eb7c bi\u1ec7t<\/td>\n<\/tr>\n<tr>\n<td>GRU (\u0110\u01a1n v\u1ecb \u0111\u1ecbnh k\u1ef3 c\u00f3 c\u1ed5ng)<\/td>\n<td>Phi\u00ean b\u1ea3n \u0111\u01a1n gi\u1ea3n c\u1ee7a LSTM<\/td>\n<\/tr>\n<tr>\n<td>RNN hai chi\u1ec1u<\/td>\n<td>X\u1eed l\u00fd tr\u00ecnh t\u1ef1 t\u1eeb c\u1ea3 hai h\u01b0\u1edbng<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n<h2>C\u00e1c c\u00e1ch s\u1eed d\u1ee5ng M\u1ea1ng th\u1ea7n kinh t\u00e1i di\u1ec5n, c\u00e1c v\u1ea5n \u0111\u1ec1 v\u00e0 gi\u1ea3i ph\u00e1p c\u1ee7a ch\u00fang<\/h2>\n<p>RNN c\u00f3 th\u1ec3 \u0111\u01b0\u1ee3c s\u1eed d\u1ee5ng cho:<\/p>\n<ul>\n<li><strong>X\u1eed l\u00fd ng\u00f4n ng\u1eef t\u1ef1 nhi\u00ean<\/strong>: Ph\u00e2n t\u00edch t\u00ecnh c\u1ea3m, d\u1ecbch thu\u1eadt.<\/li>\n<li><strong>Nh\u1eadn d\u1ea1ng gi\u1ecdng n\u00f3i<\/strong>: Phi\u00ean \u00e2m ng\u00f4n ng\u1eef n\u00f3i.<\/li>\n<li><strong>D\u1ef1 \u0111o\u00e1n chu\u1ed7i th\u1eddi gian<\/strong>: D\u1ef1 b\u00e1o gi\u00e1 c\u1ed5 phi\u1ebfu.<\/li>\n<\/ul>\n<h3>V\u1ea5n \u0111\u1ec1 v\u00e0 gi\u1ea3i ph\u00e1p:<\/h3>\n<ul>\n<li><strong>\u0110\u1ed9 d\u1ed1c bi\u1ebfn m\u1ea5t<\/strong>: \u0110\u01b0\u1ee3c gi\u1ea3i quy\u1ebft b\u1eb1ng LSTM ho\u1eb7c GRU.<\/li>\n<li><strong>\u0110\u1ed9 d\u1ed1c b\u00f9ng n\u1ed5<\/strong>: C\u1eaft b\u1edbt \u0111\u1ed9 d\u1ed1c trong qu\u00e1 tr\u00ecnh \u0111\u00e0o t\u1ea1o c\u00f3 th\u1ec3 gi\u1ea3m thi\u1ec3u \u0111i\u1ec1u n\u00e0y.<\/li>\n<\/ul>\n<h2>C\u00e1c \u0111\u1eb7c \u0111i\u1ec3m ch\u00ednh v\u00e0 nh\u1eefng so s\u00e1nh kh\u00e1c v\u1edbi c\u00e1c thu\u1eadt ng\u1eef t\u01b0\u01a1ng t\u1ef1<\/h2>\n<table>\n<thead>\n<tr>\n<th>T\u00ednh n\u0103ng<\/th>\n<th>RNN<\/th>\n<th>CNN (M\u1ea1ng th\u1ea7n kinh chuy\u1ec3n \u0111\u1ed5i)<\/th>\n<th>Chuy\u1ec3n ti\u1ebfp NN<\/th>\n<\/tr>\n<\/thead>\n<tbody>\n<tr>\n<td>X\u1eed l\u00fd tr\u00ecnh t\u1ef1<\/td>\n<td>Xu\u1ea5t s\u1eafc<\/td>\n<td>Ngh\u00e8o<\/td>\n<td>Ngh\u00e8o<\/td>\n<\/tr>\n<tr>\n<td>H\u1ec7 th\u1ed1ng ph\u00e2n c\u1ea5p kh\u00f4ng gian<\/td>\n<td>Ngh\u00e8o<\/td>\n<td>Xu\u1ea5t s\u1eafc<\/td>\n<td>T\u1ed1t<\/td>\n<\/tr>\n<tr>\n<td>\u0110\u1ed9 kh\u00f3 luy\u1ec7n t\u1eadp<\/td>\n<td>Trung b\u00ecnh \u0111\u1ebfn kh\u00f3<\/td>\n<td>V\u1eeba ph\u1ea3i<\/td>\n<td>D\u1ec5<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n<h2>Quan \u0111i\u1ec3m v\u00e0 c\u00f4ng ngh\u1ec7 c\u1ee7a t\u01b0\u01a1ng lai li\u00ean quan \u0111\u1ebfn m\u1ea1ng th\u1ea7n kinh t\u00e1i ph\u00e1t<\/h2>\n<p>RNN li\u00ean t\u1ee5c ph\u00e1t tri\u1ec3n, v\u1edbi nghi\u00ean c\u1ee9u t\u1eadp trung v\u00e0o vi\u1ec7c n\u00e2ng cao hi\u1ec7u qu\u1ea3, gi\u1ea3m th\u1eddi gian \u0111\u00e0o t\u1ea1o v\u00e0 t\u1ea1o ra ki\u1ebfn tr\u00fac ph\u00f9 h\u1ee3p cho c\u00e1c \u1ee9ng d\u1ee5ng th\u1eddi gian th\u1ef1c. \u0110i\u1ec7n to\u00e1n l\u01b0\u1ee3ng t\u1eed v\u00e0 s\u1ef1 t\u00edch h\u1ee3p RNN v\u1edbi c\u00e1c lo\u1ea1i m\u1ea1ng th\u1ea7n kinh kh\u00e1c c\u0169ng mang \u0111\u1ebfn nh\u1eefng kh\u1ea3 n\u0103ng th\u00fa v\u1ecb trong t\u01b0\u01a1ng lai.<\/p>\n<h2>C\u00e1ch s\u1eed d\u1ee5ng ho\u1eb7c li\u00ean k\u1ebft m\u00e1y ch\u1ee7 proxy v\u1edbi m\u1ea1ng th\u1ea7n kinh \u0111\u1ecbnh k\u1ef3<\/h2>\n<p>C\u00e1c m\u00e1y ch\u1ee7 proxy nh\u01b0 OneProxy c\u00f3 th\u1ec3 l\u00e0 c\u00f4ng c\u1ee5 \u0111\u00e0o t\u1ea1o RNN, \u0111\u1eb7c bi\u1ec7t l\u00e0 trong c\u00e1c t\u00e1c v\u1ee5 nh\u01b0 qu\u00e9t web \u0111\u1ec3 thu th\u1eadp d\u1eef li\u1ec7u. B\u1eb1ng c\u00e1ch cho ph\u00e9p truy c\u1eadp d\u1eef li\u1ec7u \u1ea9n danh v\u00e0 ph\u00e2n t\u00e1n, m\u00e1y ch\u1ee7 proxy c\u00f3 th\u1ec3 t\u1ea1o \u0111i\u1ec1u ki\u1ec7n thu\u1eadn l\u1ee3i cho vi\u1ec7c thu th\u1eadp c\u00e1c b\u1ed9 d\u1eef li\u1ec7u \u0111a d\u1ea1ng v\u00e0 phong ph\u00fa c\u1ea7n thi\u1ebft \u0111\u1ec3 \u0111\u00e0o t\u1ea1o c\u00e1c m\u00f4 h\u00ecnh RNN ph\u1ee9c t\u1ea1p.<\/p>\n<h2>Li\u00ean k\u1ebft li\u00ean quan<\/h2>\n<ul>\n<li><a href=\"https:\/\/www.tensorflow.org\/guide\/keras\/rnn\" target=\"_new\" rel=\"noopener nofollow\">M\u1ea1ng th\u1ea7n kinh t\u00e1i ph\u00e1t trong TensorFlow<\/a><\/li>\n<li><a href=\"https:\/\/colah.github.io\/posts\/2015-08-Understanding-LSTMs\/\" target=\"_new\" rel=\"noopener nofollow\">T\u00ecm hi\u1ec3u m\u1ea1ng LSTM<\/a><\/li>\n<li><a href=\"https:\/\/oneproxy.pro\/vn\/\" target=\"_new\" rel=\"noopener\">D\u1ecbch v\u1ee5 OneProxy \u0111\u1ec3 thu th\u1eadp d\u1eef li\u1ec7u an to\u00e0n<\/a><\/li>\n<\/ul>\n<p>(L\u01b0u \u00fd: C\u00f3 v\u1ebb nh\u01b0 \u201cM\u1ea1ng trung t\u00ednh t\u00e1i ph\u00e1t\u201d c\u00f3 th\u1ec3 l\u00e0 l\u1ed7i \u0111\u00e1nh m\u00e1y trong l\u1eddi nh\u1eafc v\u00e0 b\u00e0i b\u00e1o \u0111\u01b0\u1ee3c vi\u1ebft c\u00f3 t\u00ednh \u0111\u1ebfn \u201cM\u1ea1ng th\u1ea7n kinh t\u00e1i ph\u00e1t.\u201d)<\/p>","protected":false},"featured_media":478657,"menu_order":0,"template":"","meta":{"_acf_changed":false,"content-type":"","inline_featured_image":false,"footnotes":""},"class_list":["post-478656","wiki","type-wiki","status-publish","has-post-thumbnail","hentry"],"acf":{"faq_title":"Frequently Asked Questions about <mark>Recurrent Neural Networks (RNNs): An In-Depth Overview<\/mark>","faq_items":[{"question":"What is a Recurrent Neural Network (RNN)?","answer":"<p>A Recurrent Neural Network (RNN) is a type of artificial neural network designed to recognize patterns in sequences of data, such as text, speech, or time series data. Unlike traditional feedforward neural networks, RNNs have connections that loop back on themselves, providing a form of memory, which allows them to process variable-length sequences of inputs.<\/p>"},{"question":"When were Recurrent Neural Networks first introduced?","answer":"<p>Recurrent Neural Networks were first introduced in the 1980s by researchers like David Rumelhart, Geoffrey Hinton, and Ronald Williams. They proposed simple models for neural networks with looped connections, enabling a memory mechanism.<\/p>"},{"question":"How does the internal structure of a Recurrent Neural Network work?","answer":"<p>The internal structure of an RNN consists of input, hidden, and output layers. The hidden layer has recurrent connections that process the inputs and previous hidden state, creating a new hidden state. The output layer generates the final output based on the current hidden state. Various activation functions can be applied within the hidden layers.<\/p>"},{"question":"What are some key features of Recurrent Neural Networks?","answer":"<p>Key features of RNNs include their ability to process sequences of variable length, store information from previous time steps (memory), and adapt to various tasks like natural language processing and speech recognition. They also have training challenges such as susceptibility to vanishing and exploding gradients.<\/p>"},{"question":"What are the different types of Recurrent Neural Networks?","answer":"<p>Different types of RNNs include Vanilla RNN, LSTM (Long Short-Term Memory), GRU (Gated Recurrent Unit), and Bidirectional RNN. LSTMs and GRUs are designed to address the vanishing gradient problem, while Bidirectional RNNs process sequences from both directions.<\/p>"},{"question":"How can proxy servers like OneProxy be used with Recurrent Neural Networks?","answer":"<p>Proxy servers like OneProxy can be used in training RNNs for tasks like web scraping for data collection. By enabling anonymous and distributed data access, proxy servers facilitate the acquisition of diverse datasets necessary for training RNN models, enhancing their performance and capabilities.<\/p>"},{"question":"What are the future perspectives and technologies related to Recurrent Neural Networks?","answer":"<p>The future of RNNs is focused on enhancing efficiency, reducing training times, and developing architectures suitable for real-time applications. Research in areas like quantum computing and integration with other neural networks presents exciting possibilities for further advancements in the field.<\/p>"}]},"_links":{"self":[{"href":"https:\/\/oneproxy.pro\/vn\/wp-json\/wp\/v2\/wiki\/478656","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/oneproxy.pro\/vn\/wp-json\/wp\/v2\/wiki"}],"about":[{"href":"https:\/\/oneproxy.pro\/vn\/wp-json\/wp\/v2\/types\/wiki"}],"version-history":[{"count":0,"href":"https:\/\/oneproxy.pro\/vn\/wp-json\/wp\/v2\/wiki\/478656\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/oneproxy.pro\/vn\/wp-json\/wp\/v2\/media\/478657"}],"wp:attachment":[{"href":"https:\/\/oneproxy.pro\/vn\/wp-json\/wp\/v2\/media?parent=478656"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}