{"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/reduced-gate-convolutional-lstm-using","title":"Reduced-Gate Convolutional LSTM Using Predictive Coding for Spatiotemporal Prediction","arxiv_id":"1810.07251","date":"2018-10-16","proceeding":null,"authors":["Nelly Elsayed","Anthony S. Maida","Magdy Bayoumi"],"abstract":"Spatiotemporal sequence prediction is an important problem in deep learning.\nWe study next-frame(s) video prediction using a deep-learning-based predictive\ncoding framework that uses convolutional, long short-term memory (convLSTM)\nmodules. We introduce a novel reduced-gate convolutional LSTM (rgcLSTM)\narchitecture that requires a significantly lower parameter budget than a\ncomparable convLSTM. Our reduced-gate model achieves equal or better\nnext-frame(s) prediction accuracy than the original convolutional LSTM while\nusing a smaller parameter budget, thereby reducing training time. We tested our\nreduced gate modules within a predictive coding architecture on the moving\nMNIST and KITTI datasets. We found that our reduced-gate model has a\nsignificant reduction of approximately 40 percent of the total number of\ntraining parameters and a 25 percent redution in elapsed training time in\ncomparison with the standard convolutional LSTM model. This makes our model\nmore attractive for hardware implementation especially on small devices.","url_abs":"http://arxiv.org/abs/1810.07251v9","url_pdf":"http://arxiv.org/pdf/1810.07251v9.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":"reduced-gate-convolutional-lstm-using","repo_url":"https://github.com/NellyElsayed/rgcLSTM","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"prediction","task_name":"Prediction"},{"task_slug":"video-prediction","task_name":"Video Prediction"}],"methods":[{"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":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}