{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/batch-normalized-recurrent-highway-networks","title":"Batch-normalized Recurrent Highway Networks","arxiv_id":"1809.10271","date":"2018-09-26","proceeding":null,"authors":["Chi Zhang","Thang Nguyen","Shagan Sah","Raymond Ptucha","Alexander Loui","Carl Salvaggio"],"abstract":"Gradient control plays an important role in feed-forward networks applied to\nvarious computer vision tasks. Previous work has shown that Recurrent Highway\nNetworks minimize the problem of vanishing or exploding gradients. They achieve\nthis by setting the eigenvalues of the temporal Jacobian to 1 across the time\nsteps. In this work, batch normalized recurrent highway networks are proposed\nto control the gradient flow in an improved way for network convergence.\nSpecifically, the introduced model can be formed by batch normalizing the\ninputs at each recurrence loop. The proposed model is tested on an image\ncaptioning task using MSCOCO dataset. Experimental results indicate that the\nbatch normalized recurrent highway networks converge faster and performs better\ncompared with the traditional LSTM and RHN based models.","url_abs":"http://arxiv.org/abs/1809.10271v1","url_pdf":"http://arxiv.org/pdf/1809.10271v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"batch-normalized-recurrent-highway-networks","repo_url":"https://github.com/KurochkinAlexey/Hierarchical-Attention-Based-Recurrent-Highway-Networks-for-Time-Series-Prediction","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"image-captioning","task_name":"Image Captioning"}],"methods":[{"method_slug":"highway-networks","method_name":"Highway networks"},{"method_slug":"lstm","method_name":"LSTM"},{"method_slug":"sigmoid-activation","method_name":"Sigmoid Activation"},{"method_slug":"tanh-activation","method_name":"Tanh Activation"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}