{"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/deciding-how-to-decide-dynamic-routing-in","title":"Deciding How to Decide: Dynamic Routing in Artificial Neural Networks","arxiv_id":"1703.06217","date":"2017-03-17","proceeding":"ICML 2017 8","authors":["Mason McGill","Pietro Perona"],"abstract":"We propose and systematically evaluate three strategies for training\ndynamically-routed artificial neural networks: graphs of learned\ntransformations through which different input signals may take different paths.\nThough some approaches have advantages over others, the resulting networks are\noften qualitatively similar. We find that, in dynamically-routed networks\ntrained to classify images, layers and branches become specialized to process\ndistinct categories of images. Additionally, given a fixed computational\nbudget, dynamically-routed networks tend to perform better than comparable\nstatically-routed networks.","url_abs":"http://arxiv.org/abs/1703.06217v2","url_pdf":"http://arxiv.org/pdf/1703.06217v2.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":"deciding-how-to-decide-dynamic-routing-in","repo_url":"https://github.com/MasonMcGill/multipath-nn","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":null}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1703.06217","atlas_url":"https://app.syntology.ai/?focus=1703.06217","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1703.06217"}},"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/MasonMcGill/multipath-nn","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":"faa95c3fa93b22ab","entry":"n_leaves","repo":"MasonMcGill/multipath-nn","repo_kind":"official","path":"scripts/lib/net_types.py","file_url":"https://github.com/MasonMcGill/multipath-nn/blob/HEAD/scripts/lib/net_types.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":"faa95c3fa93b22ab"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}