{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,15]],"date-time":"2026-05-15T05:10:25Z","timestamp":1778821825859,"version":"3.51.4"},"reference-count":25,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Neurocomputing"],"published-print":{"date-parts":[[2026,8]]},"DOI":"10.1016\/j.neucom.2026.133773","type":"journal-article","created":{"date-parts":[[2026,4,25]],"date-time":"2026-04-25T15:07:48Z","timestamp":1777129668000},"page":"133773","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["Reliable yet high-speed memristor-based mixed-signal coarse-grained reconfigurable architecture for CNN inference acceleration"],"prefix":"10.1016","volume":"688","author":[{"given":"Reza","family":"Kazerooni-Zand","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ali","family":"Afzali-Kusha","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7098-6440","authenticated-orcid":false,"given":"Mehdi","family":"Kamal","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"78","reference":[{"key":"10.1016\/j.neucom.2026.133773_bib1","first-page":"14","article-title":"ISAAC: a convolutional neural network accelerator with in-situ analog arithmetic in crossbars","author":"Shafiee","year":"2016","journal-title":"Proc. - 2016 43rd Int. Symp. Comput. Archit. ISCA 2016"},{"key":"10.1016\/j.neucom.2026.133773_bib2","first-page":"715","article-title":"PUMA: a programmable ultra-efficient memristor-based accelerator for machine learning inference","author":"Ankit","year":"2019","journal-title":"Int. Conf. Archit. Support Program. Lang. Oper. Syst. - ASPLOS no. Ml"},{"key":"10.1016\/j.neucom.2026.133773_bib3","first-page":"265","article-title":"FORMS: fine-grained polarized ReRAM-based in-situ computation for mixed-signal DNN accelerator","volume":"2021","author":"Yuan","year":"2021","journal-title":"Proc. - Int. Symp. Comput. Arch."},{"issue":"1","key":"10.1016\/j.neucom.2026.133773_bib4","doi-asserted-by":"crossref","first-page":"98","DOI":"10.1109\/JXCDC.2020.2999581","article-title":"ACortex: an energy-efficient multipurpose mixed-signal inference accelerator","volume":"6","author":"Bavandpour","year":"2020","journal-title":"IEEE J. Explor. Solid-State Comput. Devices Circuits"},{"key":"10.1016\/j.neucom.2026.133773_bib5","doi-asserted-by":"crossref","unstructured":"R. Kazerooni-zand and A.L.I. Afzali-kusha, \u201cMemristive-based Mixed-signal CGRA for Accelerating Deep Neural Network Inference,\u201d 2023, doi: 10.1145\/3595638.","DOI":"10.1145\/3595638"},{"key":"10.1016\/j.neucom.2026.133773_bib6","first-page":"19","article-title":"Accelerator-friendly neural-network training: learning variations and defects in RRAM crossbar","volume":"61602300","author":"Chen","year":"2017","journal-title":"Proc. 2017 Des. Autom. Test. Eur."},{"key":"10.1016\/j.neucom.2026.133773_bib7","article-title":"Rescuing memristor-based neuromorphic design with high defects","volume":"Part 12828","author":"Liu","year":"2017","journal-title":"Proc. - Des. Autom. Conf."},{"key":"10.1016\/j.neucom.2026.133773_bib8","doi-asserted-by":"crossref","DOI":"10.1109\/LAEDC61552.2024.10555838","article-title":"Stuck-at Faults in ReRAM neuromorphic circuit array and their correction through machine learning","volume":"CiM","author":"Sawal","year":"2024","journal-title":"2024 IEEE Lat. Am. Electron Devices Conf. LAEDC 2024"},{"key":"10.1016\/j.neucom.2026.133773_bib9","first-page":"187","article-title":"Defects mitigation in resistive crossbars for analog vector matrix multiplication","volume":"2020","author":"Zhang","year":"2020","journal-title":"Proc. Asia South Pac. Des. Autom. Conf. ASP-DAC"},{"issue":"1","key":"10.1016\/j.neucom.2026.133773_bib10","doi-asserted-by":"crossref","first-page":"102","DOI":"10.1109\/JETCAS.2017.2776980","article-title":"Stuck-at fault tolerance in RRAM computing systems","volume":"8","author":"Xia","year":"2018","journal-title":"IEEE J. Emerg. Sel. Top. Circuits Syst."},{"key":"10.1016\/j.neucom.2026.133773_bib11","first-page":"545","article-title":"FSA: an efficient fault-tolerant systolic array-based DNN accelerator architecture","volume":"2022","author":"Zhao","year":"2022","journal-title":"Proc. - IEEE Int. Conf. Comput. Des. VLSI Comput. Process"},{"key":"10.1016\/j.neucom.2026.133773_bib12","first-page":"1","article-title":"Online fault-tolerance for memristive neuromorphic fabric based on local approximation","author":"Ahmed","year":"2023","journal-title":"2023 IEEE Eur. Test. Symp."},{"issue":"6","key":"10.1016\/j.neucom.2026.133773_bib13","doi-asserted-by":"crossref","first-page":"518","DOI":"10.1109\/TC.1984.1676475","article-title":"Algorithm-based fault tolerance for matrix operations","volume":"C\u201333","author":"Huang","year":"1984","journal-title":"IEEE Trans. Comput."},{"key":"10.1016\/j.neucom.2026.133773_bib14","first-page":"1","article-title":"Fault tolerance for RRAM-based matrix operations","volume":"2018","author":"Liu","year":"2018","journal-title":"Proc. - Int. Test. Conf."},{"key":"10.1016\/j.neucom.2026.133773_bib15","article-title":"A low overhead checksum technique for error correction in memristive crossbar for deep learning applications","volume":"2023","author":"Hemaram","year":"2023","journal-title":"Proc. IEEE VLSI Test. Symp."},{"key":"10.1016\/j.neucom.2026.133773_bib16","doi-asserted-by":"crossref","unstructured":"S. Hemaram, M. Mayahinia, and M.B. Tahoori, \u201cAdaptive Block Error Correction for Memristive Crossbars,\u201d 2022 IEEE 28th Int. Symp. On-Line Test. Robust Syst. Des., pp. 1\u20136, doi: 10.1109\/IOLTS56730.2022.9897817.","DOI":"10.1109\/IOLTS56730.2022.9897817"},{"key":"10.1016\/j.neucom.2026.133773_bib17","series-title":"International Conference on Electronics Circuits and Systems (ICECS)","article-title":"Making Memristive Processing-in-Memory Reliable","author":"Leitersdorf","year":"2021"},{"key":"10.1016\/j.neucom.2026.133773_bib18","doi-asserted-by":"crossref","unstructured":"S. Burel et al., \u201cZero-Overhead Protection for CNN Weights To cite this version: HAL Id: hal-03470345 Zero-Overhead Protection for CNN Weights,\u201d 2021. doi.org\/10.48550\/arXiv.2109.09687.","DOI":"10.1109\/DFT52944.2021.9568363"},{"key":"10.1016\/j.neucom.2026.133773_bib19","article-title":"Cost-effective fault tolerance for CNNs using parameter vulnerability based hardening and pruning","author":"Ahmadilivani","year":"2024","journal-title":"Proc. - 2024 IEEE 30th Int. Symp. -line Test. Robust. Syst. Des. IOLTS 2024"},{"key":"10.1016\/j.neucom.2026.133773_bib20","first-page":"1","article-title":"Drop-connect as a fault-tolerance approach for RRAM-based deep neural network accelerators","author":"Xiang","year":"2024","journal-title":"2024 IEEE 42nd VLSI Test. Symp (VTS) Tempe AZ USA"},{"issue":"12","key":"10.1016\/j.neucom.2026.133773_bib21","doi-asserted-by":"crossref","first-page":"4687","DOI":"10.1109\/TCSI.2019.2934560","article-title":"OCTAN: an on-chip training algorithm for memristive neuromorphic circuits","volume":"66","author":"Ansari","year":"2019","journal-title":"IEEE Trans. Circuits Syst. I Regul. Pap."},{"key":"10.1016\/j.neucom.2026.133773_bib22","unstructured":"North Carolina State University, \u201cFreepdk45: An open-source predictive 45nm pdk,\u201d https:\/\/eda.ncsu.edu\/freepdk\/freepdk45\/."},{"key":"10.1016\/j.neucom.2026.133773_bib23","first-page":"27","article-title":"PRIME: a novel processing-in-memory architecture for neural network computation in reram-based main memory","author":"Chi","year":"2016","journal-title":"Proc. - 2016 43rd Int. Symp. Comput. Archit. ISCA 2016"},{"key":"10.1016\/j.neucom.2026.133773_bib24","doi-asserted-by":"crossref","first-page":"557","DOI":"10.1109\/HPCA51647.2021.00054","article-title":"CAPE: a content-addressable processing engine","author":"Caminal","year":"2021","journal-title":"2021 IEEE Int. Symp High. -Perform. Comput. Archit. (HPCA) Seoul. Korea (South)"},{"key":"10.1016\/j.neucom.2026.133773_bib25","first-page":"1","article-title":"On tolerating variations and faults in memristor crossbar based neural network accelerators by network expansion and weight zeroing","author":"Yang","year":"2023","journal-title":"Proc. Asian Test. Symp."}],"container-title":["Neurocomputing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0925231226011707?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0925231226011707?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,5,15]],"date-time":"2026-05-15T04:32:10Z","timestamp":1778819530000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0925231226011707"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8]]},"references-count":25,"alternative-id":["S0925231226011707"],"URL":"https:\/\/doi.org\/10.1016\/j.neucom.2026.133773","relation":{},"ISSN":["0925-2312"],"issn-type":[{"value":"0925-2312","type":"print"}],"subject":[],"published":{"date-parts":[[2026,8]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Reliable yet high-speed memristor-based mixed-signal coarse-grained reconfigurable architecture for CNN inference acceleration","name":"articletitle","label":"Article Title"},{"value":"Neurocomputing","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.neucom.2026.133773","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier B.V. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"133773"}}