{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T15:55:10Z","timestamp":1782834910248,"version":"3.54.5"},"reference-count":34,"publisher":"Association for Computing Machinery (ACM)","issue":"5","license":[{"start":{"date-parts":[[2024,8,14]],"date-time":"2024-08-14T00:00:00Z","timestamp":1723593600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"La Region Occitanie","award":["GRAINE-SYFI"],"award-info":[{"award-number":["GRAINE-SYFI"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Embed. Comput. Syst."],"published-print":{"date-parts":[[2024,9,30]]},"abstract":"<jats:p>\n            Over the past few years, neural networks have started penetrating safety critical systems to make decisions as, for example, in robots, rockets, and autonomous driving cars. Neural networks based on floating-point arithmetic are very time and memory consuming, which are not compatible with embedded systems known to have limited resources. They are also very sensitive to the precision in which they have been trained, so changing this precision generally degrades the quality of their answers. To deal with that, we introduce a new technique to generate a fixed-point code for a trained neural network. This technique is based on fixed-point arithmetic with mixed-precision. This arithmetic is based on integer operations only, which are compatible with small memory devices. The obtained neural network has the same behavior as the initial one (based on the floating-point arithmetic) up to an error threshold defined by the user. The experimental results show the efficiency of our tool\n            <jats:monospace>SyFix<\/jats:monospace>\n            in terms of memory saved and the accuracy of the computations.\n          <\/jats:p>","DOI":"10.1145\/3563945","type":"journal-article","created":{"date-parts":[[2022,9,16]],"date-time":"2022-09-16T09:28:19Z","timestamp":1663320499000},"page":"1-28","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":8,"title":["Code Generation for Neural Networks Based on Fixed-point Arithmetic"],"prefix":"10.1145","volume":"23","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0490-2338","authenticated-orcid":false,"given":"Hanane","family":"Benmaghnia","sequence":"first","affiliation":[{"name":"University of Perpignan Via Domitia, Perpignan, France"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6238-9651","authenticated-orcid":false,"given":"Matthieu","family":"Martel","sequence":"additional","affiliation":[{"name":"University of Perpignan Via Domitia and Numalis, Perpignan, France"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2778-7555","authenticated-orcid":false,"given":"Yassamine","family":"Seladji","sequence":"additional","affiliation":[{"name":"University of Tlemcen Aboubekr Belkaid, Tlemcen, Algeria"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2024,8,14]]},"reference":[{"key":"e_1_3_2_2_1","first-page":"92","article-title":"The classification performance of RDA","author":"Aeberhard Stefan","year":"1992","unstructured":"Stefan Aeberhard, Danny Coomans, and Olivier de Vel. 1992. The classification performance of RDA. Technical report, Department of Computer Science and Department of Mathematics and Statistics, James Cook University of North Queensland, 92\u2013101.","journal-title":"Technical report, Department of Computer Science and Department of Mathematics and Statistics, James Cook University of North Queensland"},{"key":"e_1_3_2_3_1","doi-asserted-by":"publisher","DOI":"10.14311\/692"},{"key":"e_1_3_2_4_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-15497-3_9"},{"issue":"2","key":"e_1_3_2_5_1","article-title":"An application of multilayer neural network on hepatitis disease diagnosis using approximations of sigmoid activation function.","volume":"42","author":"\u00c7etin Onursal","year":"2015","unstructured":"Onursal \u00c7etin, Feyzullah Temurta\u015f, and \u015eenol G\u00fclg\u00f6n\u00fcl. 2015. An application of multilayer neural network on hepatitis disease diagnosis using approximations of sigmoid activation function. Dicle Med. J.\/Dicle Tip Dergisi 42, 2 (2015).","journal-title":"Dicle Med. J.\/Dicle Tip Dergisi"},{"key":"e_1_3_2_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/3009837.3009846"},{"key":"e_1_3_2_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCPS.2018.00028"},{"key":"e_1_3_2_8_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-77935-5_9"},{"key":"e_1_3_2_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/SP.2018.00058"},{"key":"e_1_3_2_10_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10710-017-9314-z"},{"key":"e_1_3_2_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/3314221.3314597"},{"key":"e_1_3_2_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2018.2808319"},{"key":"e_1_3_2_13_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10766-018-00626-7"},{"key":"e_1_3_2_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2012.2187914"},{"key":"e_1_3_2_15_1","first-page":"1","article-title":"IEEE standard for floating-point arithmetic","year":"2008","unstructured":"IEEE. 2008. IEEE standard for floating-point arithmetic. IEEE Std 754-2008 (2008), 1\u201370.","journal-title":"IEEE Std 754-2008"},{"key":"e_1_3_2_16_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-30281-8_8"},{"key":"e_1_3_2_17_1","volume-title":"Proceedings of the International Conference on Learning Representations","author":"Jin Qing","year":"2022","unstructured":"Qing Jin, Jian Ren, Richard Zhuang, Sumant Hanumante, Zhengang Li, Zhiyu Chen, Yanzhi Wang, Kaiyuan Yang, and Sergey Tulyakov. 2022. F8Net: Fixed-point 8-bit only multiplication for network quantization. In Proceedings of the International Conference on Learning Representations."},{"key":"e_1_3_2_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/3307681.3326608"},{"key":"e_1_3_2_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/MM.2020.3012391"},{"key":"e_1_3_2_20_1","doi-asserted-by":"publisher","DOI":"10.5555\/1468074"},{"key":"e_1_3_2_21_1","doi-asserted-by":"publisher","DOI":"10.5555\/100511"},{"key":"e_1_3_2_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/ARITH48897.2020.00023"},{"key":"e_1_3_2_23_1","first-page":"2849","volume-title":"Proceedings of the 33nd International Conference on Machine Learning (ICML\u201916) (JMLR Workshop and Conference Proceedings)","volume":"48","author":"Lin Darryl Dexu","year":"2016","unstructured":"Darryl Dexu Lin, Sachin S. Talathi, and V. Sreekanth Annapureddy. 2016. Fixed point quantization of deep convolutional networks. In Proceedings of the 33nd International Conference on Machine Learning (ICML\u201916) (JMLR Workshop and Conference Proceedings), Maria-Florina Balcan and Kilian Q. Weinberger (Eds.), Vol. 48. JMLR.org, 2849\u20132858."},{"key":"e_1_3_2_24_1","volume-title":"Impl\u00e9mentation optimale de filtres lin\u00e9aires en arithm\u00e9tique virgule fixe. (Optimal implementation of linear filters in fixed-point arithmetic)","author":"Lopez Benoit","year":"2014","unstructured":"Benoit Lopez. 2014. Impl\u00e9mentation optimale de filtres lin\u00e9aires en arithm\u00e9tique virgule fixe. (Optimal implementation of linear filters in fixed-point arithmetic). Ph.D. Dissertation. Pierre and Marie Curie University, Paris, France."},{"key":"e_1_3_2_25_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-76526-6"},{"key":"e_1_3_2_26_1","volume-title":"Synthesis of certified programs in fixed-point arithmetic, and its application to linear algebra basic blocks.","author":"Najahi Mohamed Amine","year":"2014","unstructured":"Mohamed Amine Najahi. 2014. Synthesis of certified programs in fixed-point arithmetic, and its application to linear algebra basic blocks.Ph.D. Dissertation. University of Perpignan, France."},{"key":"e_1_3_2_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/3290354"},{"key":"e_1_3_2_28_1","unstructured":"Youcheng Sun Xiaowei Huang Daniel Kroening James Sharp Matthew Hill and Rob Ashmore. 2018. Testing deep neural networks. Retrieved from https:\/\/arXiv:1803.04792."},{"key":"e_1_3_2_29_1","doi-asserted-by":"publisher","DOI":"10.5121\/ijsc.2012.3107"},{"key":"e_1_3_2_30_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-53288-8_1"},{"key":"e_1_3_2_31_1","volume-title":"Field-programmable Gate Array Technology","author":"Trimberger Stephen M.","year":"2012","unstructured":"Stephen M. Trimberger. 2012. Field-programmable Gate Array Technology. Springer Science & Business Media."},{"key":"e_1_3_2_32_1","unstructured":"Caterina Urban and Antoine Min\u00e9. 2021. A review of formal methods applied to machine learning. Retrieved from https:\/\/arxiv.org\/abs\/2104.02466."},{"key":"e_1_3_2_33_1","volume-title":"ML2R Coding Nuggets: Solving Linear Programming Problems","author":"Welke Pascal","year":"2020","unstructured":"Pascal Welke and Christian Bauckhage. 2020. ML2R Coding Nuggets: Solving Linear Programming Problems. Technical Report. MLAI, University of Bonn."},{"key":"e_1_3_2_34_1","unstructured":"William H. Wolberg W. Nick Street and Olvi L. Mangasarian. 1992. Breast Cancer Wisconsin (Diagnostic) Data Set Retrieved from http:\/\/archive.ics.uci.edu\/ml\/."},{"issue":"83","key":"e_1_3_2_35_1","first-page":"198","article-title":"Fixed-point arithmetic: An introduction","volume":"81","author":"Yates Randy","year":"2009","unstructured":"Randy Yates. 2009. Fixed-point arithmetic: An introduction. Digital Signal Labs 81, 83 (2009), 198.","journal-title":"Digital Signal Labs"}],"container-title":["ACM Transactions on Embedded Computing Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3563945","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3563945","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T18:08:15Z","timestamp":1750183695000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3563945"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,8,14]]},"references-count":34,"journal-issue":{"issue":"5","published-print":{"date-parts":[[2024,9,30]]}},"alternative-id":["10.1145\/3563945"],"URL":"https:\/\/doi.org\/10.1145\/3563945","relation":{},"ISSN":["1539-9087","1558-3465"],"issn-type":[{"value":"1539-9087","type":"print"},{"value":"1558-3465","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,8,14]]},"assertion":[{"value":"2022-01-31","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2022-09-09","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2024-08-14","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}