{"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/adaptive-computation-time-for-recurrent","title":"Adaptive Computation Time for Recurrent Neural Networks","arxiv_id":"1603.08983","date":"2016-03-29","proceeding":null,"authors":["Alex Graves"],"abstract":"This paper introduces Adaptive Computation Time (ACT), an algorithm that\nallows recurrent neural networks to learn how many computational steps to take\nbetween receiving an input and emitting an output. ACT requires minimal changes\nto the network architecture, is deterministic and differentiable, and does not\nadd any noise to the parameter gradients. Experimental results are provided for\nfour synthetic problems: determining the parity of binary vectors, applying\nbinary logic operations, adding integers, and sorting real numbers. Overall,\nperformance is dramatically improved by the use of ACT, which successfully\nadapts the number of computational steps to the requirements of the problem. We\nalso present character-level language modelling results on the Hutter prize\nWikipedia dataset. In this case ACT does not yield large gains in performance;\nhowever it does provide intriguing insight into the structure of the data, with\nmore computation allocated to harder-to-predict transitions, such as spaces\nbetween words and ends of sentences. This suggests that ACT or other adaptive\ncomputation methods could provide a generic method for inferring segment\nboundaries in sequence data.","url_abs":"http://arxiv.org/abs/1603.08983v6","url_pdf":"http://arxiv.org/pdf/1603.08983v6.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":"adaptive-computation-time-for-recurrent","repo_url":"https://github.com/andreamad8/Universal-Transformer-Pytorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"adaptive-computation-time-for-recurrent","repo_url":"https://github.com/ceyzaguirre4/adaptive_computation","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"adaptive-computation-time-for-recurrent","repo_url":"https://github.com/google/evojax","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"jax","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"adaptive-computation-time-for-recurrent","repo_url":"https://github.com/widmi/widis-lstm-tools","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"GPL-3.0"}},{"paper_slug":"adaptive-computation-time-for-recurrent","repo_url":"https://github.com/labmlai/annotated_deep_learning_paper_implementations","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"language-modelling","task_name":"Language Modelling"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1603.08983","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1603.08983"}},"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/andreamad8/Universal-Transformer-Pytorch","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/google/evojax","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/widmi/widis-lstm-tools","reach":{"status":"ok","spdx":"GPL-3.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/labmlai/annotated_deep_learning_paper_implementations","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/ceyzaguirre4/adaptive_computation","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_violates":1,"unverified":3},"by_repo_kind":{"listed":{"samples":4,"ran":1,"repositories":2}},"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":"095dea140acd99f6","entry":"get_attn_key_pad_mask","repo":"andreamad8/Universal-Transformer-Pytorch","repo_kind":"listed","path":"models/UTransformer.py","file_url":"https://github.com/andreamad8/Universal-Transformer-Pytorch/blob/HEAD/models/UTransformer.py","link_basis":"first_harvest_node","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"095dea140acd99f6"}},{"code_sha256_prefix":"58caec2a4f1159dc","entry":"get_path","repo":"ceyzaguirre4/adaptive_computation","repo_kind":"listed","path":"act/utils.py","file_url":"https://github.com/ceyzaguirre4/adaptive_computation/blob/HEAD/act/utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"58caec2a4f1159dc"}},{"code_sha256_prefix":"ad8b210c90bf993e","entry":"pad_batch","repo":"ceyzaguirre4/adaptive_computation","repo_kind":"listed","path":"act/utils.py","file_url":"https://github.com/ceyzaguirre4/adaptive_computation/blob/HEAD/act/utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"ad8b210c90bf993e"}},{"code_sha256_prefix":"4ba0c3a66ce30058","entry":"pad_tensor","repo":"ceyzaguirre4/adaptive_computation","repo_kind":"listed","path":"act/utils.py","file_url":"https://github.com/ceyzaguirre4/adaptive_computation/blob/HEAD/act/utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"4ba0c3a66ce30058"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}