{"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/deep-fried-convnets","title":"Deep Fried Convnets","arxiv_id":"1412.7149","date":"2014-12-22","proceeding":"ICCV 2015 12","authors":["Zichao Yang","Marcin Moczulski","Misha Denil","Nando de Freitas","Alex Smola","Le Song","Ziyu Wang"],"abstract":"The fully connected layers of a deep convolutional neural network typically\ncontain over 90% of the network parameters, and consume the majority of the\nmemory required to store the network parameters. Reducing the number of\nparameters while preserving essentially the same predictive performance is\ncritically important for operating deep neural networks in memory constrained\nenvironments such as GPUs or embedded devices.\n  In this paper we show how kernel methods, in particular a single Fastfood\nlayer, can be used to replace all fully connected layers in a deep\nconvolutional neural network. This novel Fastfood layer is also end-to-end\ntrainable in conjunction with convolutional layers, allowing us to combine them\ninto a new architecture, named deep fried convolutional networks, which\nsubstantially reduces the memory footprint of convolutional networks trained on\nMNIST and ImageNet with no drop in predictive performance.","url_abs":"http://arxiv.org/abs/1412.7149v4","url_pdf":"http://arxiv.org/pdf/1412.7149v4.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":"deep-fried-convnets","repo_url":"https://github.com/v0lta/wavelet-network-compression","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"image-classification","task_name":"Image Classification"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/image-classification-on-mnist","task":"Image Classification","dataset":"MNIST","model":"Deep Fried Convnets","rank_in_archive_order":44,"of":81,"metrics":{"Percentage error":"0.7"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1412.7149","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}