{"id":2274,"date":"2026-04-01T11:41:33","date_gmt":"2026-04-01T15:41:33","guid":{"rendered":"https:\/\/wp.well-e.org\/publication\/should-we-reconsider-rnns-for-time-series-forecasting\/"},"modified":"2026-04-30T20:41:56","modified_gmt":"2026-05-01T00:41:56","slug":"should-we-reconsider-rnns-for-time-series-forecasting","status":"publish","type":"publication","link":"https:\/\/wp.well-e.org\/fr\/publication\/should-we-reconsider-rnns-for-time-series-forecasting\/","title":{"rendered":"Should We Reconsider RNNs for Time-Series Forecasting?"},"content":{"rendered":"<p><strong>Authors:<\/strong> Vahid Naghashi and Mounir Boukadoum and Abdoulaye Banire Diallo<\/p>\n<p><strong>Date:<\/strong> 2025-04-01<\/p>\n<p><strong>Journal:<\/strong> AI<\/p>\n<p><strong>Status:<\/strong> Published<\/p>\n<hr>\n<p>(1) Background: In recent years, Transformer-based models have dominated the time-series forecasting domain, overshadowing recurrent neural networks (RNNs) such as Long Short-Term Memory (LSTM) and Gated Recurrent Unit (GRU). While Transformers demonstrate superior performance, their high computational cost limits their practical application in resource-constrained settings. (2) Methods: In this paper, we reconsider RNNs\u2014specifically the GRU architecture\u2014as an efficient alternative to time-series forecasting by leveraging this architecture\u2019s sequential representation capability to capture cross-channel dependencies effectively. Our model also utilizes a feed-forward layer right after the GRU module to represent temporal dependencies, and aggregates it with the GRU layers to predict future values of a given time-series. (3) Results and conclusions: Our extensive experiments conducted on different real-world datasets show that our inverted GRU (iGRU) model achieves promising results in terms of error metrics and memory efficiency, challenging or surpassing state-of-the-art models on various benchmarks.<\/p>\n","protected":false},"template":"","meta":{"_acf_changed":false,"_crdt_document":""},"class_list":["post-2274","publication","type-publication","status-publish","hentry"],"blocksy_meta":[],"acf":[],"yoast_head":"<!-- This site is optimized with the Yoast SEO plugin v27.5 - https:\/\/yoast.com\/product\/yoast-seo-wordpress\/ -->\n<title>Should We Reconsider RNNs for Time-Series Forecasting? - WELL-E<\/title>\n<meta name=\"robots\" content=\"index, follow, max-snippet:-1, max-image-preview:large, max-video-preview:-1\" \/>\n<link rel=\"canonical\" href=\"https:\/\/wp.well-e.org\/fr\/publication\/should-we-reconsider-rnns-for-time-series-forecasting\/\" \/>\n<meta property=\"og:locale\" content=\"fr_CA\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"Should We Reconsider RNNs for Time-Series Forecasting? - WELL-E\" \/>\n<meta property=\"og:description\" content=\"Authors: Vahid Naghashi and Mounir Boukadoum and Abdoulaye Banire Diallo Date: 2025-04-01 Journal: AI Status: Published (1) Background: In recent years, Transformer-based models have dominated the time-series forecasting domain, overshadowing recurrent neural networks (RNNs) such as Long Short-Term Memory (LSTM) and Gated Recurrent Unit (GRU). While Transformers demonstrate superior performance, their high computational cost limits [&hellip;]\" \/>\n<meta property=\"og:url\" content=\"https:\/\/wp.well-e.org\/fr\/publication\/should-we-reconsider-rnns-for-time-series-forecasting\/\" \/>\n<meta property=\"og:site_name\" content=\"WELL-E\" \/>\n<meta property=\"article:modified_time\" content=\"2026-05-01T00:41:56+00:00\" \/>\n<meta name=\"twitter:card\" content=\"summary_large_image\" \/>\n<meta name=\"twitter:label1\" content=\"Est. reading time\" \/>\n\t<meta name=\"twitter:data1\" content=\"1 minute\" \/>\n<script type=\"application\/ld+json\" class=\"yoast-schema-graph\">{\"@context\":\"https:\\\/\\\/schema.org\",\"@graph\":[{\"@type\":\"WebPage\",\"@id\":\"https:\\\/\\\/wp.well-e.org\\\/publication\\\/should-we-reconsider-rnns-for-time-series-forecasting\\\/\",\"url\":\"https:\\\/\\\/wp.well-e.org\\\/publication\\\/should-we-reconsider-rnns-for-time-series-forecasting\\\/\",\"name\":\"Should We Reconsider RNNs for Time-Series Forecasting? - WELL-E\",\"isPartOf\":{\"@id\":\"https:\\\/\\\/wp.well-e.org\\\/#website\"},\"datePublished\":\"2026-04-01T15:41:33+00:00\",\"dateModified\":\"2026-05-01T00:41:56+00:00\",\"breadcrumb\":{\"@id\":\"https:\\\/\\\/wp.well-e.org\\\/publication\\\/should-we-reconsider-rnns-for-time-series-forecasting\\\/#breadcrumb\"},\"inLanguage\":\"fr-CA\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\\\/\\\/wp.well-e.org\\\/publication\\\/should-we-reconsider-rnns-for-time-series-forecasting\\\/\"]}]},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\\\/\\\/wp.well-e.org\\\/publication\\\/should-we-reconsider-rnns-for-time-series-forecasting\\\/#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"Home\",\"item\":\"https:\\\/\\\/wp.well-e.org\\\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"Publications\",\"item\":\"https:\\\/\\\/wp.well-e.org\\\/publication\\\/\"},{\"@type\":\"ListItem\",\"position\":3,\"name\":\"Should We Reconsider RNNs for Time-Series Forecasting?\"}]},{\"@type\":\"WebSite\",\"@id\":\"https:\\\/\\\/wp.well-e.org\\\/#website\",\"url\":\"https:\\\/\\\/wp.well-e.org\\\/\",\"name\":\"WELL-E\",\"description\":\"IA au service du bien-&ecirc;tre animal\",\"publisher\":{\"@id\":\"https:\\\/\\\/wp.well-e.org\\\/#organization\"},\"potentialAction\":[{\"@type\":\"SearchAction\",\"target\":{\"@type\":\"EntryPoint\",\"urlTemplate\":\"https:\\\/\\\/wp.well-e.org\\\/?s={search_term_string}\"},\"query-input\":{\"@type\":\"PropertyValueSpecification\",\"valueRequired\":true,\"valueName\":\"search_term_string\"}}],\"inLanguage\":\"fr-CA\"},{\"@type\":\"Organization\",\"@id\":\"https:\\\/\\\/wp.well-e.org\\\/#organization\",\"name\":\"WELL-E\",\"url\":\"https:\\\/\\\/wp.well-e.org\\\/\",\"logo\":{\"@type\":\"ImageObject\",\"inLanguage\":\"fr-CA\",\"@id\":\"https:\\\/\\\/wp.well-e.org\\\/#\\\/schema\\\/logo\\\/image\\\/\",\"url\":\"https:\\\/\\\/wp.well-e.org\\\/wp-content\\\/uploads\\\/2024\\\/05\\\/LOGOTYPETAG_Left_RVB_FR-edited-1-e1718738358443.png\",\"contentUrl\":\"https:\\\/\\\/wp.well-e.org\\\/wp-content\\\/uploads\\\/2024\\\/05\\\/LOGOTYPETAG_Left_RVB_FR-edited-1-e1718738358443.png\",\"width\":1000,\"height\":250,\"caption\":\"WELL-E\"},\"image\":{\"@id\":\"https:\\\/\\\/wp.well-e.org\\\/#\\\/schema\\\/logo\\\/image\\\/\"},\"sameAs\":[\"https:\\\/\\\/www.linkedin.com\\\/company\\\/research-and-innovation-chair-in-animal-welfare-and-artificial-intelligence-well-e\"]}]}<\/script>\n<!-- \/ Yoast SEO plugin. -->","yoast_head_json":{"title":"Should We Reconsider RNNs for Time-Series Forecasting? - WELL-E","robots":{"index":"index","follow":"follow","max-snippet":"max-snippet:-1","max-image-preview":"max-image-preview:large","max-video-preview":"max-video-preview:-1"},"canonical":"https:\/\/wp.well-e.org\/fr\/publication\/should-we-reconsider-rnns-for-time-series-forecasting\/","og_locale":"fr_CA","og_type":"article","og_title":"Should We Reconsider RNNs for Time-Series Forecasting? - WELL-E","og_description":"Authors: Vahid Naghashi and Mounir Boukadoum and Abdoulaye Banire Diallo Date: 2025-04-01 Journal: AI Status: Published (1) Background: In recent years, Transformer-based models have dominated the time-series forecasting domain, overshadowing recurrent neural networks (RNNs) such as Long Short-Term Memory (LSTM) and Gated Recurrent Unit (GRU). While Transformers demonstrate superior performance, their high computational cost limits [&hellip;]","og_url":"https:\/\/wp.well-e.org\/fr\/publication\/should-we-reconsider-rnns-for-time-series-forecasting\/","og_site_name":"WELL-E","article_modified_time":"2026-05-01T00:41:56+00:00","twitter_card":"summary_large_image","twitter_misc":{"Est. reading time":"1 minute"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"WebPage","@id":"https:\/\/wp.well-e.org\/publication\/should-we-reconsider-rnns-for-time-series-forecasting\/","url":"https:\/\/wp.well-e.org\/publication\/should-we-reconsider-rnns-for-time-series-forecasting\/","name":"Should We Reconsider RNNs for Time-Series Forecasting? - WELL-E","isPartOf":{"@id":"https:\/\/wp.well-e.org\/#website"},"datePublished":"2026-04-01T15:41:33+00:00","dateModified":"2026-05-01T00:41:56+00:00","breadcrumb":{"@id":"https:\/\/wp.well-e.org\/publication\/should-we-reconsider-rnns-for-time-series-forecasting\/#breadcrumb"},"inLanguage":"fr-CA","potentialAction":[{"@type":"ReadAction","target":["https:\/\/wp.well-e.org\/publication\/should-we-reconsider-rnns-for-time-series-forecasting\/"]}]},{"@type":"BreadcrumbList","@id":"https:\/\/wp.well-e.org\/publication\/should-we-reconsider-rnns-for-time-series-forecasting\/#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https:\/\/wp.well-e.org\/"},{"@type":"ListItem","position":2,"name":"Publications","item":"https:\/\/wp.well-e.org\/publication\/"},{"@type":"ListItem","position":3,"name":"Should We Reconsider RNNs for Time-Series Forecasting?"}]},{"@type":"WebSite","@id":"https:\/\/wp.well-e.org\/#website","url":"https:\/\/wp.well-e.org\/","name":"WELL-E","description":"IA au service du bien-&ecirc;tre animal","publisher":{"@id":"https:\/\/wp.well-e.org\/#organization"},"potentialAction":[{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https:\/\/wp.well-e.org\/?s={search_term_string}"},"query-input":{"@type":"PropertyValueSpecification","valueRequired":true,"valueName":"search_term_string"}}],"inLanguage":"fr-CA"},{"@type":"Organization","@id":"https:\/\/wp.well-e.org\/#organization","name":"WELL-E","url":"https:\/\/wp.well-e.org\/","logo":{"@type":"ImageObject","inLanguage":"fr-CA","@id":"https:\/\/wp.well-e.org\/#\/schema\/logo\/image\/","url":"https:\/\/wp.well-e.org\/wp-content\/uploads\/2024\/05\/LOGOTYPETAG_Left_RVB_FR-edited-1-e1718738358443.png","contentUrl":"https:\/\/wp.well-e.org\/wp-content\/uploads\/2024\/05\/LOGOTYPETAG_Left_RVB_FR-edited-1-e1718738358443.png","width":1000,"height":250,"caption":"WELL-E"},"image":{"@id":"https:\/\/wp.well-e.org\/#\/schema\/logo\/image\/"},"sameAs":["https:\/\/www.linkedin.com\/company\/research-and-innovation-chair-in-animal-welfare-and-artificial-intelligence-well-e"]}]}},"_links":{"self":[{"href":"https:\/\/wp.well-e.org\/fr\/wp-json\/wp\/v2\/publication\/2274","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/wp.well-e.org\/fr\/wp-json\/wp\/v2\/publication"}],"about":[{"href":"https:\/\/wp.well-e.org\/fr\/wp-json\/wp\/v2\/types\/publication"}],"wp:attachment":[{"href":"https:\/\/wp.well-e.org\/fr\/wp-json\/wp\/v2\/media?parent=2274"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}