{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"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":{"syntology_url":"https://syntology.ai/paper/1412.7149","atlas_url":"https://app.syntology.ai/?focus=1412.7149","mcp":null,"developers":"https://syntology.ai/developers","held":true,"reason":"arxiv_id_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"agent_calls":[{"tool":"get_citation_path","arguments":{"paper_1":"1412.7149"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"1412.7149\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"1412.7149"},"call":"get_concepts_for_paper(arxiv_id=\"1412.7149\")"}],"by_repo":[{"repo":"v0lta/wavelet-network-compression","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0}],"by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"7a368a439bcdefd56233b8e8e5b3ce25b14a4fa5b5ff316a1702e32f512f5091","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}