{"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/how-can-we-be-so-dense-the-benefits-of-using","title":"How Can We Be So Dense? The Benefits of Using Highly Sparse Representations","arxiv_id":"1903.11257","date":"2019-03-27","proceeding":null,"authors":["Subutai Ahmad","Luiz Scheinkman"],"abstract":"Most artificial networks today rely on dense representations, whereas\nbiological networks rely on sparse representations. In this paper we show how\nsparse representations can be more robust to noise and interference, as long as\nthe underlying dimensionality is sufficiently high. A key intuition that we\ndevelop is that the ratio of the operable volume around a sparse vector divided\nby the volume of the representational space decreases exponentially with\ndimensionality. We then analyze computationally efficient sparse networks\ncontaining both sparse weights and activations. Simulations on MNIST and the\nGoogle Speech Command Dataset show that such networks demonstrate significantly\nimproved robustness and stability compared to dense networks, while maintaining\ncompetitive accuracy. We discuss the potential benefits of sparsity on\naccuracy, noise robustness, hyperparameter tuning, learning speed,\ncomputational efficiency, and power requirements.","url_abs":"http://arxiv.org/abs/1903.11257v2","url_pdf":"http://arxiv.org/pdf/1903.11257v2.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":"how-can-we-be-so-dense-the-benefits-of-using","repo_url":"https://github.com/numenta/htmpapers","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"AGPL-3.0"}},{"paper_slug":"how-can-we-be-so-dense-the-benefits-of-using","repo_url":"https://github.com/hyeon95y/sparselinear","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"how-can-we-be-so-dense-the-benefits-of-using","repo_url":"https://github.com/marty1885/sparsenet-pytorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"computational-efficiency","task_name":"Computational Efficiency"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1903.11257","atlas_url":"https://app.syntology.ai/?focus=1903.11257","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1903.11257"}},"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/numenta/htmpapers","reach":{"status":"ok","spdx":"AGPL-3.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/hyeon95y/sparselinear","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/marty1885/sparsenet-pytorch","reach":null}],"summary":{"ran_draft_wrong":2,"ran_honours":1,"ran_fixture":1},"by_repo_kind":{"listed":{"samples":3,"ran":3,"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":4,"samples":[{"code_sha256_prefix":"0272b62d02ccdfe7","entry":"fgsm_attack","repo":"marty1885/sparsenet-pytorch","repo_kind":"listed","path":"ifgsm.py","file_url":"https://github.com/marty1885/sparsenet-pytorch/blob/HEAD/ifgsm.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"0272b62d02ccdfe7"}},{"code_sha256_prefix":"319e4b577e33102d","entry":"foolbox_attack","repo":"marty1885/sparsenet-pytorch","repo_kind":"listed","path":"fb.py","file_url":"https://github.com/marty1885/sparsenet-pytorch/blob/HEAD/fb.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":"319e4b577e33102d"}},{"code_sha256_prefix":"48d5d7aad76726a7","entry":"ifgsm_attack","repo":"marty1885/sparsenet-pytorch","repo_kind":"listed","path":"ifgsm.py","file_url":"https://github.com/marty1885/sparsenet-pytorch/blob/HEAD/ifgsm.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"48d5d7aad76726a7"}},{"code_sha256_prefix":"3a0749baa452d466","entry":"small_world_chunker","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"3a0749baa452d466"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}