{"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/distributed-deep-neural-networks-over-the","title":"Distributed Deep Neural Networks over the Cloud, the Edge and End Devices","arxiv_id":"1709.01921","date":"2017-09-06","proceeding":null,"authors":["Surat Teerapittayanon","Bradley McDanel","H. T. Kung"],"abstract":"We propose distributed deep neural networks (DDNNs) over distributed\ncomputing hierarchies, consisting of the cloud, the edge (fog) and end devices.\nWhile being able to accommodate inference of a deep neural network (DNN) in the\ncloud, a DDNN also allows fast and localized inference using shallow portions\nof the neural network at the edge and end devices. When supported by a scalable\ndistributed computing hierarchy, a DDNN can scale up in neural network size and\nscale out in geographical span. Due to its distributed nature, DDNNs enhance\nsensor fusion, system fault tolerance and data privacy for DNN applications. In\nimplementing a DDNN, we map sections of a DNN onto a distributed computing\nhierarchy. By jointly training these sections, we minimize communication and\nresource usage for devices and maximize usefulness of extracted features which\nare utilized in the cloud. The resulting system has built-in support for\nautomatic sensor fusion and fault tolerance. As a proof of concept, we show a\nDDNN can exploit geographical diversity of sensors to improve object\nrecognition accuracy and reduce communication cost. In our experiment, compared\nwith the traditional method of offloading raw sensor data to be processed in\nthe cloud, DDNN locally processes most sensor data on end devices while\nachieving high accuracy and is able to reduce the communication cost by a\nfactor of over 20x.","url_abs":"http://arxiv.org/abs/1709.01921v1","url_pdf":"http://arxiv.org/pdf/1709.01921v1.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":"distributed-deep-neural-networks-over-the","repo_url":"https://github.com/kunglab/ddnn","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"distributed-computing","task_name":"Distributed Computing"},{"task_slug":"object-recognition","task_name":"Object Recognition"},{"task_slug":"sensor-fusion","task_name":"Sensor Fusion"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1709.01921","atlas_url":"https://app.syntology.ai/?focus=1709.01921","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1709.01921"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/kunglab/ddnn","reach":null}],"summary":{"ran_honours":1},"by_repo_kind":{"official":{"samples":1,"ran":1,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":1,"samples":[{"code_sha256_prefix":"9d7624b4b4f6fe48","entry":"max_acc","repo":"kunglab/ddnn","repo_kind":"official","path":"exp/exp_combining.py","file_url":"https://github.com/kunglab/ddnn/blob/HEAD/exp/exp_combining.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"9d7624b4b4f6fe48"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}