{"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/machine-learning-on-sequential-data-using-a","title":"Machine Learning on Sequential Data Using a Recurrent Weighted Average","arxiv_id":"1703.01253","date":"2017-03-03","proceeding":null,"authors":["Jared Ostmeyer","Lindsay Cowell"],"abstract":"Recurrent Neural Networks (RNN) are a type of statistical model designed to\nhandle sequential data. The model reads a sequence one symbol at a time. Each\nsymbol is processed based on information collected from the previous symbols.\nWith existing RNN architectures, each symbol is processed using only\ninformation from the previous processing step. To overcome this limitation, we\npropose a new kind of RNN model that computes a recurrent weighted average\n(RWA) over every past processing step. Because the RWA can be computed as a\nrunning average, the computational overhead scales like that of any other RNN\narchitecture. The approach essentially reformulates the attention mechanism\ninto a stand-alone model. The performance of the RWA model is assessed on the\nvariable copy problem, the adding problem, classification of artificial\ngrammar, classification of sequences by length, and classification of the MNIST\nimages (where the pixels are read sequentially one at a time). On almost every\ntask, the RWA model is found to outperform a standard LSTM model.","url_abs":"http://arxiv.org/abs/1703.01253v5","url_pdf":"http://arxiv.org/pdf/1703.01253v5.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":"machine-learning-on-sequential-data-using-a","repo_url":"https://github.com/jostmey/rwa","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"machine-learning-on-sequential-data-using-a","repo_url":"https://github.com/theSage21/torchcircus","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"machine-learning","task_name":"BIG-bench Machine Learning"},{"task_slug":"classification-1","task_name":"Classification"},{"task_slug":"classification","task_name":"General Classification"}],"methods":[{"method_slug":"lstm","method_name":"LSTM"},{"method_slug":"sigmoid-activation","method_name":"Sigmoid Activation"},{"method_slug":"tanh-activation","method_name":"Tanh Activation"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1703.01253","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1703.01253"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+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/jostmey/rwa","reach":{"status":"ok","spdx":"NOASSERTION"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/theSage21/torchcircus","reach":null}],"summary":{"ran_draft_wrong":5,"ran_honours":1},"by_repo_kind":{"listed":{"samples":6,"ran":6,"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":6,"samples":[{"code_sha256_prefix":"f0d780ae83015e9f","entry":"generate_dataset","repo":"theSage21/torchcircus","repo_kind":"listed","path":"rwa/addition.py","file_url":"https://github.com/theSage21/torchcircus/blob/HEAD/rwa/addition.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":"f0d780ae83015e9f"}},{"code_sha256_prefix":"3c8215dfb3c4731f","entry":"generate_datasets","repo":"theSage21/torchcircus","repo_kind":"listed","path":"rwa/sequence_length.py","file_url":"https://github.com/theSage21/torchcircus/blob/HEAD/rwa/sequence_length.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"3c8215dfb3c4731f"}},{"code_sha256_prefix":"eb1c0a097b38eadf","entry":"generate_pair","repo":"theSage21/torchcircus","repo_kind":"listed","path":"rwa/sequence_length.py","file_url":"https://github.com/theSage21/torchcircus/blob/HEAD/rwa/sequence_length.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"eb1c0a097b38eadf"}},{"code_sha256_prefix":"e2f9c6f4c4df2b9f","entry":"make_invalid","repo":"theSage21/torchcircus","repo_kind":"listed","path":"rwa/classifying_artificial_grammar.py","file_url":"https://github.com/theSage21/torchcircus/blob/HEAD/rwa/classifying_artificial_grammar.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"e2f9c6f4c4df2b9f"}},{"code_sha256_prefix":"6d9920ad1dddf1f0","entry":"make_train_and_dev_dataset","repo":"theSage21/torchcircus","repo_kind":"listed","path":"rwa/classifying_artificial_grammar.py","file_url":"https://github.com/theSage21/torchcircus/blob/HEAD/rwa/classifying_artificial_grammar.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":"6d9920ad1dddf1f0"}},{"code_sha256_prefix":"62dfaf949c7a6e17","entry":"one_hot","repo":"theSage21/torchcircus","repo_kind":"listed","path":"rwa/classifying_artificial_grammar.py","file_url":"https://github.com/theSage21/torchcircus/blob/HEAD/rwa/classifying_artificial_grammar.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":"62dfaf949c7a6e17"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}