{"id":478085,"date":"2023-08-09T09:27:13","date_gmt":"2023-08-09T09:27:13","guid":{"rendered":""},"modified":"2023-09-05T11:16:02","modified_gmt":"2023-09-05T11:16:02","slug":"multitask-learning","status":"publish","type":"wiki","link":"https:\/\/oneproxy.pro\/vn\/wiki\/multitask-learning\/","title":{"rendered":"H\u1ecdc \u0111a nhi\u1ec7m"},"content":{"rendered":"<p>Th\u00f4ng tin t\u00f3m t\u1eaft v\u1ec1 h\u1ecdc \u0111a nhi\u1ec7m<\/p>\n<p>H\u1ecdc \u0111a nhi\u1ec7m (MTL) l\u00e0 m\u1ed9t l\u0129nh v\u1ef1c h\u1ecdc m\u00e1y trong \u0111\u00f3 m\u1ed9t m\u00f4 h\u00ecnh \u0111\u01b0\u1ee3c \u0111\u00e0o t\u1ea1o \u0111\u1ec3 th\u1ef1c hi\u1ec7n \u0111\u1ed3ng th\u1eddi nhi\u1ec1u nhi\u1ec7m v\u1ee5 li\u00ean quan. \u0110i\u1ec1u n\u00e0y tr\u00e1i ng\u01b0\u1ee3c v\u1edbi c\u00e1c ph\u01b0\u01a1ng ph\u00e1p h\u1ecdc t\u1eadp truy\u1ec1n th\u1ed1ng, trong \u0111\u00f3 m\u1ed7i nhi\u1ec7m v\u1ee5 \u0111\u01b0\u1ee3c gi\u1ea3i quy\u1ebft m\u1ed9t c\u00e1ch \u0111\u1ed9c l\u1eadp. MTL t\u1eadn d\u1ee5ng th\u00f4ng tin c\u00f3 trong nhi\u1ec1u nhi\u1ec7m v\u1ee5 li\u00ean quan \u0111\u1ec3 gi\u00fap c\u1ea3i thi\u1ec7n hi\u1ec7u qu\u1ea3 h\u1ecdc t\u1eadp v\u00e0 \u0111\u1ed9 ch\u00ednh x\u00e1c d\u1ef1 \u0111o\u00e1n c\u1ee7a m\u00f4 h\u00ecnh.<\/p>\n<h2>L\u1ecbch s\u1eed ngu\u1ed3n g\u1ed1c c\u1ee7a vi\u1ec7c h\u1ecdc \u0111a nhi\u1ec7m v\u00e0 s\u1ef1 \u0111\u1ec1 c\u1eadp \u0111\u1ea7u ti\u00ean v\u1ec1 n\u00f3<\/h2>\n<p>Kh\u00e1i ni\u1ec7m h\u1ecdc t\u1eadp \u0111a nhi\u1ec7m xu\u1ea5t hi\u1ec7n v\u00e0o \u0111\u1ea7u nh\u1eefng n\u0103m 1990 v\u1edbi t\u00e1c ph\u1ea9m c\u1ee7a Rich Caruana. B\u00e0i vi\u1ebft chuy\u00ean \u0111\u1ec1 c\u1ee7a Caruana n\u0103m 1997 \u0111\u00e3 cung c\u1ea5p m\u1ed9t khu\u00f4n kh\u1ed5 n\u1ec1n t\u1ea3ng cho vi\u1ec7c h\u1ecdc nhi\u1ec1u nhi\u1ec7m v\u1ee5 b\u1eb1ng c\u00e1ch s\u1eed d\u1ee5ng c\u00e1ch tr\u00ecnh b\u00e0y chung. \u00dd t\u01b0\u1edfng \u0111\u1eb1ng sau MTL \u0111\u01b0\u1ee3c l\u1ea5y c\u1ea3m h\u1ee9ng t\u1eeb c\u00e1ch con ng\u01b0\u1eddi c\u00f9ng nhau h\u1ecdc c\u00e1c nhi\u1ec7m v\u1ee5 kh\u00e1c nhau v\u00e0 c\u1ea3i thi\u1ec7n t\u1eebng nhi\u1ec7m v\u1ee5 b\u1eb1ng c\u00e1ch hi\u1ec3u \u0111\u01b0\u1ee3c nh\u1eefng \u0111i\u1ec3m chung c\u1ee7a h\u1ecd.<\/p>\n<h2>Th\u00f4ng tin chi ti\u1ebft v\u1ec1 H\u1ecdc \u0111a nhi\u1ec7m: M\u1edf r\u1ed9ng ch\u1ee7 \u0111\u1ec1<\/h2>\n<p>H\u1ecdc t\u1eadp \u0111a nhi\u1ec7m nh\u1eb1m m\u1ee5c \u0111\u00edch khai th\u00e1c nh\u1eefng \u0111i\u1ec3m t\u01b0\u01a1ng \u0111\u1ed3ng v\u00e0 kh\u00e1c bi\u1ec7t gi\u1eefa c\u00e1c nhi\u1ec7m v\u1ee5 \u0111\u1ec3 c\u1ea3i thi\u1ec7n hi\u1ec7u su\u1ea5t. \u0110i\u1ec1u n\u00e0y \u0111\u01b0\u1ee3c th\u1ef1c hi\u1ec7n b\u1eb1ng c\u00e1ch t\u00ecm m\u1ed9t c\u00e1ch tr\u00ecnh b\u00e0y n\u1eafm b\u1eaft th\u00f4ng tin h\u1eefu \u00edch trong c\u00e1c nhi\u1ec7m v\u1ee5 kh\u00e1c nhau. C\u00e1ch bi\u1ec3u di\u1ec5n chung n\u00e0y cho ph\u00e9p m\u00f4 h\u00ecnh t\u00ecm hi\u1ec3u c\u00e1c t\u00ednh n\u0103ng t\u1ed5ng qu\u00e1t h\u01a1n v\u00e0 th\u01b0\u1eddng d\u1eabn \u0111\u1ebfn hi\u1ec7u su\u1ea5t t\u1ed1t h\u01a1n.<\/p>\n<h3>L\u1ee3i \u00edch c\u1ee7a MTL:<\/h3>\n<ul>\n<li>C\u1ea3i thi\u1ec7n kh\u00e1i qu\u00e1t h\u00f3a.<\/li>\n<li>Gi\u1ea3m nguy c\u01a1 trang b\u1ecb qu\u00e1 m\u1ee9c.<\/li>\n<li>Hi\u1ec7u qu\u1ea3 h\u1ecdc t\u1eadp nh\u1edd s\u1ef1 bi\u1ec3u di\u1ec5n \u0111\u01b0\u1ee3c chia s\u1ebb.<\/li>\n<\/ul>\n<h2>C\u1ea5u tr\u00fac b\u00ean trong c\u1ee7a vi\u1ec7c h\u1ecdc \u0111a nhi\u1ec7m: C\u00e1ch th\u1ee9c ho\u1ea1t \u0111\u1ed9ng<\/h2>\n<p>Trong H\u1ecdc \u0111a nhi\u1ec7m, c\u00e1c nhi\u1ec7m v\u1ee5 kh\u00e1c nhau chia s\u1ebb m\u1ed9t s\u1ed1 ho\u1eb7c t\u1ea5t c\u1ea3 c\u00e1c l\u1edbp c\u1ee7a m\u00f4 h\u00ecnh, trong khi c\u00e1c l\u1edbp kh\u00e1c c\u00f3 nhi\u1ec7m v\u1ee5 c\u1ee5 th\u1ec3. C\u1ea5u tr\u00fac n\u00e0y cho ph\u00e9p m\u00f4 h\u00ecnh t\u00ecm hi\u1ec3u c\u00e1c t\u00ednh n\u0103ng \u0111\u01b0\u1ee3c chia s\u1ebb gi\u1eefa c\u00e1c nhi\u1ec7m v\u1ee5 kh\u00e1c nhau trong khi v\u1eabn duy tr\u00ec kh\u1ea3 n\u0103ng chuy\u00ean m\u00f4n h\u00f3a khi c\u1ea7n thi\u1ebft.<\/p>\n<h3>Ki\u1ebfn tr\u00fac \u0111i\u1ec3n h\u00ecnh:<\/h3>\n<ol>\n<li><strong>L\u1edbp chia s\u1ebb<\/strong>: C\u00e1c l\u1edbp n\u00e0y t\u00ecm hi\u1ec3u nh\u1eefng \u0111i\u1ec3m t\u01b0\u01a1ng \u0111\u1ed3ng gi\u1eefa c\u00e1c nhi\u1ec7m v\u1ee5.<\/li>\n<li><strong>C\u00e1c l\u1edbp d\u00e0nh ri\u00eang cho nhi\u1ec7m v\u1ee5<\/strong>: C\u00e1c l\u1edbp n\u00e0y cho ph\u00e9p m\u00f4 h\u00ecnh t\u00ecm hi\u1ec3u c\u00e1c t\u00ednh n\u0103ng duy nh\u1ea5t cho t\u1eebng nhi\u1ec7m v\u1ee5.<\/li>\n<\/ol>\n<h2>Ph\u00e2n t\u00edch c\u00e1c t\u00ednh n\u0103ng ch\u00ednh c\u1ee7a h\u1ecdc t\u1eadp \u0111a nhi\u1ec7m<\/h2>\n<ul>\n<li><strong>M\u1ed1i quan h\u1ec7 nhi\u1ec7m v\u1ee5<\/strong>: Hi\u1ec3u c\u00e1ch c\u00e1c nhi\u1ec7m v\u1ee5 li\u00ean quan v\u1edbi nhau l\u00e0 r\u1ea5t quan tr\u1ecdng.<\/li>\n<li><strong>Ki\u1ebfn tr\u00fac m\u00f4 h\u00ecnh<\/strong>: Vi\u1ec7c thi\u1ebft k\u1ebf m\u1ed9t m\u00f4 h\u00ecnh c\u00f3 th\u1ec3 x\u1eed l\u00fd nhi\u1ec1u nhi\u1ec7m v\u1ee5 \u0111\u00f2i h\u1ecfi ph\u1ea3i xem x\u00e9t c\u1ea9n th\u1eadn c\u00e1c th\u00e0nh ph\u1ea7n \u0111\u01b0\u1ee3c chia s\u1ebb v\u00e0 d\u00e0nh ri\u00eang cho nhi\u1ec7m v\u1ee5.<\/li>\n<li><strong>Ch\u00ednh quy<\/strong>: Ph\u1ea3i \u0111\u1ea1t \u0111\u01b0\u1ee3c s\u1ef1 c\u00e2n b\u1eb1ng gi\u1eefa c\u00e1c t\u00ednh n\u0103ng d\u00f9ng chung v\u00e0 d\u00e0nh ri\u00eang cho nhi\u1ec7m v\u1ee5.<\/li>\n<li><strong>Hi\u1ec7u qu\u1ea3<\/strong>: \u0110\u00e0o t\u1ea1o tr\u00ean nhi\u1ec1u nhi\u1ec7m v\u1ee5 c\u00f9ng l\u00fac c\u00f3 th\u1ec3 hi\u1ec7u qu\u1ea3 h\u01a1n v\u1ec1 m\u1eb7t t\u00ednh to\u00e1n.<\/li>\n<\/ul>\n<h2>C\u00e1c lo\u1ea1i h\u00ecnh h\u1ecdc t\u1eadp \u0111a nhi\u1ec7m: T\u1ed5ng quan<\/h2>\n<p>B\u1ea3ng sau minh h\u1ecda c\u00e1c lo\u1ea1i MTL kh\u00e1c nhau:<\/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>Chia s\u1ebb th\u00f4ng s\u1ed1 c\u1ee9ng<\/td>\n<td>C\u00e1c l\u1edbp gi\u1ed1ng nhau \u0111\u01b0\u1ee3c s\u1eed d\u1ee5ng cho t\u1ea5t c\u1ea3 c\u00e1c t\u00e1c v\u1ee5<\/td>\n<\/tr>\n<tr>\n<td>Chia s\u1ebb th\u00f4ng s\u1ed1 m\u1ec1m<\/td>\n<td>Nhi\u1ec7m v\u1ee5 chia s\u1ebb m\u1ed9t s\u1ed1 nh\u01b0ng kh\u00f4ng ph\u1ea3i t\u1ea5t c\u1ea3 c\u00e1c tham s\u1ed1<\/td>\n<\/tr>\n<tr>\n<td>Ph\u00e2n c\u1ee5m t\u00e1c v\u1ee5<\/td>\n<td>Nhi\u1ec7m v\u1ee5 \u0111\u01b0\u1ee3c nh\u00f3m d\u1ef1a tr\u00ean s\u1ef1 t\u01b0\u01a1ng \u0111\u1ed3ng<\/td>\n<\/tr>\n<tr>\n<td>H\u1ecdc t\u1eadp \u0111a nhi\u1ec7m theo c\u1ea5p b\u1eadc<\/td>\n<td>H\u1ecdc t\u1eadp \u0111a nhi\u1ec7m v\u1edbi h\u1ec7 th\u1ed1ng ph\u00e2n c\u1ea5p nhi\u1ec7m v\u1ee5<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n<h2>C\u00e1ch s\u1eed d\u1ee5ng H\u1ecdc t\u1eadp \u0111a nhi\u1ec7m, c\u00e1c v\u1ea5n \u0111\u1ec1 v\u00e0 gi\u1ea3i ph\u00e1p c\u1ee7a ch\u00fang<\/h2>\n<h3>C\u00f4ng d\u1ee5ng:<\/h3>\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, v.v.<\/li>\n<li><strong>T\u1ea7m nh\u00ecn m\u00e1y t\u00ednh<\/strong>: Ph\u00e1t hi\u1ec7n \u0111\u1ed1i t\u01b0\u1ee3ng, ph\u00e2n \u0111o\u1ea1n, v.v.<\/li>\n<li><strong>Ch\u0103m s\u00f3c s\u1ee9c kh\u1ecfe<\/strong>: D\u1ef1 \u0111o\u00e1n nhi\u1ec1u k\u1ebft qu\u1ea3 y t\u1ebf.<\/li>\n<\/ul>\n<h3>C\u00e1c v\u1ea5n \u0111\u1ec1:<\/h3>\n<ul>\n<li><strong>M\u1ea5t c\u00e2n b\u1eb1ng nhi\u1ec7m v\u1ee5<\/strong>: M\u1ed9t nhi\u1ec7m v\u1ee5 c\u00f3 th\u1ec3 chi ph\u1ed1i qu\u00e1 tr\u00ecnh h\u1ecdc t\u1eadp.<\/li>\n<li><strong>Chuy\u1ec3n giao ti\u00eau c\u1ef1c<\/strong>: H\u1ecdc t\u1eeb m\u1ed9t nhi\u1ec7m v\u1ee5 c\u00f3 th\u1ec3 g\u00e2y t\u1ed5n h\u1ea1i \u0111\u1ebfn hi\u1ec7u su\u1ea5t c\u1ee7a m\u1ed9t nhi\u1ec7m v\u1ee5 kh\u00e1c.<\/li>\n<\/ul>\n<h3>C\u00e1c gi\u1ea3i ph\u00e1p:<\/h3>\n<ul>\n<li><strong>Ch\u1ee9c n\u0103ng gi\u1ea3m c\u00e2n<\/strong>: \u0110\u1ec3 c\u00e2n b\u1eb1ng t\u1ea7m quan tr\u1ecdng c\u1ee7a c\u00e1c nhi\u1ec7m v\u1ee5 kh\u00e1c nhau.<\/li>\n<li><strong>L\u1ef1a ch\u1ecdn nhi\u1ec7m v\u1ee5 c\u1ea9n th\u1eadn<\/strong>: \u0110\u1ea3m b\u1ea3o r\u1eb1ng c\u00e1c nhi\u1ec7m v\u1ee5 c\u00f3 li\u00ean quan.<\/li>\n<\/ul>\n<h2>\u0110\u1eb7c \u0111i\u1ec3m ch\u00ednh v\u00e0 nh\u1eefng so s\u00e1nh kh\u00e1c<\/h2>\n<p>So s\u00e1nh H\u1ecdc t\u1eadp \u0111a nhi\u1ec7m v\u1edbi H\u1ecdc t\u1eadp m\u1ed9t nhi\u1ec7m v\u1ee5:<\/p>\n<table>\n<thead>\n<tr>\n<th>T\u00ednh n\u0103ng<\/th>\n<th>H\u1ecdc \u0111a nhi\u1ec7m<\/th>\n<th>H\u1ecdc t\u1eadp m\u1ed9t nhi\u1ec7m v\u1ee5<\/th>\n<\/tr>\n<\/thead>\n<tbody>\n<tr>\n<td>S\u1ef1 kh\u00e1i qu\u00e1t<\/td>\n<td>Th\u01b0\u1eddng th\u00ec t\u1ed1t h\u01a1n<\/td>\n<td>C\u00f3 th\u1ec3 ngh\u00e8o h\u01a1n<\/td>\n<\/tr>\n<tr>\n<td>\u0110\u1ed9 ph\u1ee9c t\u1ea1p<\/td>\n<td>Cao h\u01a1n<\/td>\n<td>Th\u1ea5p h\u01a1n<\/td>\n<\/tr>\n<tr>\n<td>Nguy c\u01a1 trang b\u1ecb qu\u00e1 m\u1ee9c<\/td>\n<td>Th\u1ea5p h\u01a1n<\/td>\n<td>Cao h\u01a1n<\/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 h\u1ecdc t\u1eadp \u0111a nhi\u1ec7m<\/h2>\n<p>C\u00e1c h\u01b0\u1edbng \u0111i trong t\u01b0\u01a1ng lai bao g\u1ed3m:<\/p>\n<ul>\n<li>Ph\u00e1t tri\u1ec3n c\u00e1c m\u00f4 h\u00ecnh m\u1ea1nh m\u1ebd h\u01a1n.<\/li>\n<li>T\u1ef1 \u0111\u1ed9ng kh\u00e1m ph\u00e1 c\u00e1c m\u1ed1i quan h\u1ec7 nhi\u1ec7m v\u1ee5.<\/li>\n<li>T\u00edch h\u1ee3p v\u1edbi c\u00e1c m\u00f4 h\u00ecnh h\u1ecdc m\u00e1y kh\u00e1c nh\u01b0 H\u1ecdc t\u0103ng c\u01b0\u1eddng.<\/li>\n<\/ul>\n<h2>C\u00e1ch s\u1eed d\u1ee5ng ho\u1eb7c li\u00ean k\u1ebft m\u00e1y ch\u1ee7 proxy v\u1edbi vi\u1ec7c h\u1ecdc \u0111a nhi\u1ec7m<\/h2>\n<p>C\u00e1c m\u00e1y ch\u1ee7 proxy nh\u01b0 OneProxy c\u00f3 th\u1ec3 \u0111\u00f3ng vai tr\u00f2 trong vi\u1ec7c h\u1ecdc \u0111a nhi\u1ec7m b\u1eb1ng c\u00e1ch t\u1ea1o \u0111i\u1ec1u ki\u1ec7n thu\u1eadn l\u1ee3i cho vi\u1ec7c thu th\u1eadp d\u1eef li\u1ec7u tr\u00ean nhi\u1ec1u mi\u1ec1n kh\u00e1c nhau. H\u1ecd c\u00f3 th\u1ec3 gi\u00fap thu th\u1eadp d\u1eef li\u1ec7u \u0111a d\u1ea1ng v\u00e0 ph\u00f9 h\u1ee3p v\u1ec1 m\u1eb7t \u0111\u1ecba l\u00fd cho c\u00e1c nhi\u1ec7m v\u1ee5 nh\u01b0 ph\u00e2n t\u00edch t\u00ecnh c\u1ea3m ho\u1eb7c d\u1ef1 \u0111o\u00e1n xu h\u01b0\u1edbng th\u1ecb tr\u01b0\u1eddng.<\/p>\n<h2>Li\u00ean k\u1ebft li\u00ean quan<\/h2>\n<ul>\n<li><a href=\"http:\/\/www.cs.cornell.edu\/~caruana\/mlj97.pdf\" target=\"_new\" rel=\"noopener nofollow\">B\u00e0i vi\u1ebft n\u0103m 1997 c\u1ee7a Rich Caruana v\u1ec1 H\u1ecdc t\u1eadp \u0111a nhi\u1ec7m<\/a><\/li>\n<li><a href=\"https:\/\/oneproxy.pro\/vn\/\" target=\"_new\" rel=\"noopener\">Trang web c\u1ee7a OneProxy v\u1ec1 c\u00e1c gi\u1ea3i ph\u00e1p proxy n\u00e2ng cao<\/a><\/li>\n<li><a href=\"https:\/\/towardsdatascience.com\/multi-task-learning-in-deep-neural-networks-eb3dfdf81739\" target=\"_new\" rel=\"noopener nofollow\">Gi\u1edbi thi\u1ec7u v\u1ec1 H\u1ecdc t\u1eadp \u0111a nhi\u1ec7m trong M\u1ea1ng l\u01b0\u1edbi th\u1ea7n kinh s\u00e2u<\/a><\/li>\n<\/ul>","protected":false},"featured_media":468967,"menu_order":0,"template":"","meta":{"_acf_changed":false,"content-type":"","inline_featured_image":false,"footnotes":""},"class_list":["post-478085","wiki","type-wiki","status-publish","has-post-thumbnail","hentry"],"acf":{"faq_title":"Frequently Asked Questions about <mark>Multitask Learning: A Comprehensive Guide<\/mark>","faq_items":[{"question":"What is Multitask Learning (MTL)?","answer":"<p>Multitask Learning (MTL) is a machine learning approach where a model is trained to perform multiple related tasks simultaneously. It leverages information contained in multiple related tasks to improve learning efficiency and predictive accuracy.<\/p>"},{"question":"When did Multitask Learning originate?","answer":"<p>Multitask Learning emerged in the early 1990s with the work of Rich Caruana, who published a foundational paper on the subject in 1997.<\/p>"},{"question":"What are the benefits of using Multitask Learning?","answer":"<p>MTL offers several benefits, such as improved generalization, a reduction in the risk of overfitting, and learning efficiency due to shared representations between different tasks.<\/p>"},{"question":"How does Multitask Learning work?","answer":"<p>Multitask Learning involves using shared layers that learn commonalities between tasks, along with task-specific layers that specialize in features unique to each task. This combination allows the model to learn shared features while also specializing where necessary.<\/p>"},{"question":"What are the key features of Multitask Learning?","answer":"<p>Key features of MTL include understanding task relationships, designing appropriate model architecture, balancing shared and task-specific features, and achieving computational efficiency.<\/p>"},{"question":"What types of Multitask Learning exist?","answer":"<p>Types of Multitask Learning include Hard Parameter Sharing (same layers used for all tasks), Soft Parameter Sharing (tasks share some but not all parameters), Task Clustering (tasks are grouped based on similarities), and Hierarchical Multitask Learning (MTL with a hierarchy of tasks).<\/p>"},{"question":"How is Multitask Learning used in various fields, and what are its challenges?","answer":"<p>MTL is used in fields like Natural Language Processing, Computer Vision, and Healthcare. Challenges include task imbalance, where one task may dominate learning, and negative transfer, where learning from one task might harm another. Solutions include weighting loss functions and careful task selection.<\/p>"},{"question":"What are the future prospects for Multitask Learning?","answer":"<p>Future directions in MTL include developing more robust models, automatically discovering task relationships, and integrating with other machine learning paradigms like Reinforcement Learning.<\/p>"},{"question":"How can proxy servers like OneProxy be associated with Multitask Learning?","answer":"<p>Proxy servers like OneProxy can be used with Multitask Learning to facilitate data collection across various domains. They can assist in gathering diverse and geographically relevant data for different tasks, such as sentiment analysis or market trend prediction.<\/p>"}]},"_links":{"self":[{"href":"https:\/\/oneproxy.pro\/vn\/wp-json\/wp\/v2\/wiki\/478085","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\/478085\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/oneproxy.pro\/vn\/wp-json\/wp\/v2\/media\/468967"}],"wp:attachment":[{"href":"https:\/\/oneproxy.pro\/vn\/wp-json\/wp\/v2\/media?parent=478085"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}