{"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/effective-quantization-methods-for-recurrent","title":"Effective Quantization Methods for Recurrent Neural Networks","arxiv_id":"1611.10176","date":"2016-11-30","proceeding":null,"authors":["Qinyao He","He Wen","Shuchang Zhou","Yuxin Wu","Cong Yao","Xinyu Zhou","Yuheng Zou"],"abstract":"Reducing bit-widths of weights, activations, and gradients of a Neural\nNetwork can shrink its storage size and memory usage, and also allow for faster\ntraining and inference by exploiting bitwise operations. However, previous\nattempts for quantization of RNNs show considerable performance degradation\nwhen using low bit-width weights and activations. In this paper, we propose\nmethods to quantize the structure of gates and interlinks in LSTM and GRU\ncells. In addition, we propose balanced quantization methods for weights to\nfurther reduce performance degradation. Experiments on PTB and IMDB datasets\nconfirm effectiveness of our methods as performances of our models match or\nsurpass the previous state-of-the-art of quantized RNN.","url_abs":"http://arxiv.org/abs/1611.10176v1","url_pdf":"http://arxiv.org/pdf/1611.10176v1.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":"effective-quantization-methods-for-recurrent","repo_url":"https://github.com/hqythu/bit-rnn","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"effective-quantization-methods-for-recurrent","repo_url":"https://github.com/qinyao-he/bit-rnn","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"quantization","task_name":"Quantization"}],"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=1611.10176","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1611.10176"}},"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/qinyao-he/bit-rnn","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/hqythu/bit-rnn","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"unverified":4},"by_repo_kind":{"official":{"samples":4,"ran":0,"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":0,"samples":[{"code_sha256_prefix":"6b5153b06d692476","entry":"ptb_producer","repo":"hqythu/bit-rnn","repo_kind":"official","path":"reader.py","file_url":"https://github.com/hqythu/bit-rnn/blob/HEAD/reader.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"6b5153b06d692476"}},{"code_sha256_prefix":"b42caa004183832c","entry":"ptb_raw_data","repo":"hqythu/bit-rnn","repo_kind":"official","path":"reader.py","file_url":"https://github.com/hqythu/bit-rnn/blob/HEAD/reader.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"b42caa004183832c"}},{"code_sha256_prefix":"478ff2a4a7db0507","entry":"quantize_w","repo":"hqythu/bit-rnn","repo_kind":"official","path":"bit_utils.py","file_url":"https://github.com/hqythu/bit-rnn/blob/HEAD/bit_utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"478ff2a4a7db0507"}},{"code_sha256_prefix":"f63276d2f1cf3b44","entry":"round_bit","repo":"hqythu/bit-rnn","repo_kind":"official","path":"bit_utils.py","file_url":"https://github.com/hqythu/bit-rnn/blob/HEAD/bit_utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"f63276d2f1cf3b44"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}