{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,22]],"date-time":"2025-10-22T10:49:19Z","timestamp":1761130159642,"version":"3.37.3"},"reference-count":39,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"12","license":[{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"French National Research Agency Low-Energy onchip Pre-processing for Activity Recognition","award":["ANR-18-CE24-0006-01"],"award-info":[{"award-number":["ANR-18-CE24-0006-01"]}]},{"name":"Nano 2022\u2013Important Projects of Common European Interest (IPCEI) Program"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Circuits Syst. I"],"published-print":{"date-parts":[[2024,12]]},"DOI":"10.1109\/tcsi.2024.3480154","type":"journal-article","created":{"date-parts":[[2024,10,28]],"date-time":"2024-10-28T17:45:48Z","timestamp":1730137548000},"page":"6470-6481","source":"Crossref","is-referenced-by-count":1,"title":["An Incremental Time-Domain Mixed-Signal Matrix-Vector-Multiplication Technique for Low-Power Edge-AI"],"prefix":"10.1109","volume":"71","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2838-4494","authenticated-orcid":false,"given":"K\u00e9vin","family":"H\u00e9riss\u00e9","sequence":"first","affiliation":[{"name":"CNRS, Centrale Lille, Junia, Univ. Lille, Univ. Polytechnique Hauts-de-France, UMR 8520-IEMN, Lille, France"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2501-8656","authenticated-orcid":false,"given":"Benoit","family":"Larras","sequence":"additional","affiliation":[{"name":"CNRS, Centrale Lille, Junia, Univ. Lille, Univ. Polytechnique Hauts-de-France, UMR 8520-IEMN, Lille, France"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0500-2892","authenticated-orcid":false,"given":"Bruno","family":"Stefanelli","sequence":"additional","affiliation":[{"name":"CNRS, Centrale Lille, Junia, Univ. Lille, Univ. Polytechnique Hauts-de-France, UMR 8520-IEMN, Lille, France"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0377-7408","authenticated-orcid":false,"given":"Andreas","family":"Kaiser","sequence":"additional","affiliation":[{"name":"CNRS, Centrale Lille, Junia, Univ. Lille, Univ. Polytechnique Hauts-de-France, UMR 8520-IEMN, Lille, France"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0977-549X","authenticated-orcid":false,"given":"Antoine","family":"Frapp\u00e9","sequence":"additional","affiliation":[{"name":"CNRS, Centrale Lille, Junia, Univ. Lille, Univ. Polytechnique Hauts-de-France, UMR 8520-IEMN, Lille, France"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","first-page":"1","article-title":"Efficient keyword spotting through hardware-aware conditional execution of deep neural networks","volume-title":"Proc. IEEE\/ACS 16th Int. Conf. Comput. Syst. Appl. (AICCSA)","author":"Giraldo"},{"key":"ref2","article-title":"What is the state of neural network pruning?","author":"Blalock","year":"2020","journal-title":"arXiv:2003.03033"},{"key":"ref3","article-title":"Deep compression: Compressing deep neural networks with pruning, trained quantization and Huffman coding","author":"Han","year":"2015","journal-title":"arXiv:1510.00149"},{"article-title":"ACIQ: Analytical clipping for integer quantization of neural networks","volume-title":"Proc. f\u00e9vr, Consult\u00e9 le","author":"Banner","key":"ref4"},{"key":"ref5","first-page":"4466","article-title":"Accurate post training quantization with small calibration sets","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Hubara"},{"key":"ref6","first-page":"7197","article-title":"Up or down? Adaptive rounding for post-training quantization","volume-title":"Proc. 37th Int. Conf. Mach. Learn.","author":"Nagel"},{"key":"ref7","article-title":"A white paper on neural network quantization","author":"Nagel","year":"2021","journal-title":"arXiv:2106.08295"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01225-0_36"},{"key":"ref9","article-title":"Deep residual learning for image recognition","author":"He","year":"2015","journal-title":"arXiv:1512.03385"},{"key":"ref10","first-page":"16318","article-title":"Overcoming oscillations in quantization-aware training","volume-title":"Proc. 39th Int. Conf. Mach. Learn.","author":"Nagel"},{"key":"ref11","article-title":"MobileNets: Efficient convolutional neural networks for mobile vision applications","author":"Howard","year":"2017","journal-title":"arXiv:1704.04861"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-023-10464-w"},{"issue":"1","key":"ref13","doi-asserted-by":"crossref","first-page":"151","DOI":"10.1109\/JSSC.2020.3029097","article-title":"A 510-nW wake-up keyword-spotting chip using serial-FFT-based MFCC and binarized depthwise separable CNN in 28-nm CMOS","volume":"56","author":"Shan","year":"2021","journal-title":"IEEE J. Solid-State Circuits"},{"issue":"6","key":"ref14","doi-asserted-by":"crossref","first-page":"1764","DOI":"10.1109\/JSSC.2019.2894360","article-title":"Design of an always-on deep neural network-based 1-\u03bcW voice activity detector aided with a customized software model for analog feature extraction","volume":"54","author":"Yang","year":"2019","journal-title":"IEEE J. Solid-State Circuits"},{"issue":"3","key":"ref15","doi-asserted-by":"crossref","first-page":"65","DOI":"10.1109\/MSSC.2022.3182935","article-title":"Digital versus analog artificial intelligence accelerators: Advances, trends, and emerging designs","volume":"14","author":"Seo","year":"2022","journal-title":"IEEE Solid State Circuits Mag."},{"key":"ref16","first-page":"1","article-title":"A 5-nm 254-TOPS\/W 221-TOPS\/mm2 fully-digital computing-in-memory macro supporting wide-range dynamic-voltage-frequency scaling and simultaneous MAC and write operations","volume-title":"IEEE Int. Solid-State Circuits Conf. (ISSCC) Dig. Tech. Papers","author":"Fujiwara"},{"issue":"8","key":"ref17","doi-asserted-by":"crossref","first-page":"2560","DOI":"10.1109\/JSSC.2022.3148273","article-title":"STICKER-IM: A 65 nm computing-in-memory NN processor using block-wise sparsity optimization and inter\/intra-macro data reuse","volume":"57","author":"Yue","year":"2022","journal-title":"IEEE J. Solid-State Circuits"},{"issue":"1","key":"ref18","doi-asserted-by":"crossref","first-page":"3","DOI":"10.1109\/TVLSI.2020.3020286","article-title":"Mixed-signal computing for deep neural network inference","volume":"29","author":"Murmann","year":"2021","journal-title":"IEEE Trans. Very Large Scale Integr. (VLSI) Syst."},{"issue":"10","key":"ref19","doi-asserted-by":"crossref","first-page":"2730","DOI":"10.1109\/JSSC.2019.2926649","article-title":"An 8 bit 12.4 TOPS\/W phase-domain MAC circuit for energy-constrained deep learning accelerators","volume":"54","author":"Toyama","year":"2019","journal-title":"IEEE J. Solid-State Circuits"},{"issue":"1","key":"ref20","doi-asserted-by":"crossref","first-page":"60","DOI":"10.1109\/JSSC.2019.2939888","article-title":"A 12.08-TOPS\/W all-digital time-domain CNN engine using bi-directional memory delay lines for energy efficient edge computing","volume":"55","author":"Sayal","year":"2020","journal-title":"IEEE J. Solid-State Circuits"},{"issue":"10","key":"ref21","doi-asserted-by":"crossref","first-page":"2944","DOI":"10.1109\/JSSC.2022.3182699","article-title":"FlashMAC: A time-frequency hybrid MAC architecture with variable latency-aware scheduling for TinyML systems","volume":"57","author":"Gweon","year":"2022","journal-title":"IEEE J. Solid-State Circuits"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/JSSC.2021.3092759"},{"key":"ref23","first-page":"1","article-title":"A 40 nm 60.64TOPS\/W ECC-capable compute-in-memory\/digital 2.25 MB\/768 KB RRAM\/SRAM system with embedded cortex M3 microprocessor for edge recommendation systems","volume-title":"IEEE Int. Solid-State Circuits Conf. (ISSCC) Dig. Tech. Papers","author":"Chang"},{"issue":"3","key":"ref24","doi-asserted-by":"crossref","first-page":"335","DOI":"10.1109\/LED.2021.3055017","article-title":"Four-bits-per-memory one-transistor-and-eight-resistive-random-access-memory (1T8R) array","volume":"42","author":"Hsieh","year":"2021","journal-title":"IEEE Electron Device Lett."},{"key":"ref25","first-page":"21","article-title":"An 8-bit, 16 input, 3.2 pJ\/op switched-capacitor dot product circuit in 28-nm FDSOI CMOS","volume-title":"Proc. IEEE Asian Solid-State Circuits Conf. (A-SSCC)","author":"Bankman"},{"issue":"6","key":"ref26","doi-asserted-by":"crossref","first-page":"1789","DOI":"10.1109\/JSSC.2019.2899730","article-title":"A 64-tile 2.4-Mb in-memory-computing CNN accelerator employing charge-domain compute","volume":"54","author":"Valavi","year":"2019","journal-title":"IEEE J. Solid-State Circuits"},{"issue":"6","key":"ref27","first-page":"1733","article-title":"XNOR-SRAM: In-memory computing SRAM macro for binary\/ternary deep neural networks","volume":"55","author":"Yin","year":"2020","journal-title":"IEEE J. Solid-State Circuits"},{"issue":"4","key":"ref28","doi-asserted-by":"crossref","first-page":"915","DOI":"10.1109\/JSSC.2016.2642198","article-title":"In-memory computation of a machine-learning classifier in a standard 6T SRAM array","volume":"52","author":"Zhang","year":"2017","journal-title":"IEEE J. Solid-State Circuits"},{"issue":"2","key":"ref29","doi-asserted-by":"crossref","first-page":"642","DOI":"10.1109\/JSSC.2017.2782087","article-title":"A multi-functional in-memory inference processor using a standard 6T SRAM array","volume":"53","author":"Kang","year":"2018","journal-title":"IEEE J. Solid-State Circuits"},{"issue":"1","key":"ref30","doi-asserted-by":"crossref","first-page":"217","DOI":"10.1109\/JSSC.2018.2880918","article-title":"CONV-SRAM: An energy-efficient SRAM with in-memory dot-product computation for low-power convolutional neural networks","volume":"54","author":"Biswas","year":"2019","journal-title":"IEEE J. Solid-State Circuits"},{"key":"ref31","first-page":"236","article-title":"A programmable neural-network inference accelerator based on scalable in-memory computing","volume-title":"IEEE Int. Solid-State Circuits Conf. (ISSCC) Dig. Tech. Papers","volume":"64","author":"Jia"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ISCAS.1990.112505"},{"key":"ref33","first-page":"22.2.1","article-title":"Towards 10000TOPS\/W DNN inference with analog in-memory computing\u2014A circuit blueprint, device options and requirements","volume-title":"IEDM Tech. Dig.","author":"Cosemans"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/JSSC.2022.3199077"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/isscc42614.2022.9731681"},{"key":"ref36","first-page":"196","article-title":"A 0.85 fJ\/conversion-step 10b 200 kS\/s subranging SAR ADC in 40 nm CMOS","volume-title":"IEEE Int. Solid-State Circuits Conf. (ISSCC) Dig. Tech. Papers","author":"Tai"},{"key":"ref37","first-page":"C74","article-title":"A 0.2\u20138 MS\/s 10b flexible SAR ADC achieving 0.35\u20132.5 fJ\/conv-step and using self-quenched dynamic bias comparator","volume-title":"Proc. Symp. VLSI Circuits","author":"Bindra"},{"volume-title":"ADC Performance Survey 1997\u20132024","author":"Murmann","key":"ref38"},{"issue":"1","key":"ref39","doi-asserted-by":"crossref","first-page":"303","DOI":"10.1109\/JSSC.2022.3200515","article-title":"8-b precision 8-Mb ReRAM compute-in-memory macro using direct-current-free time-domain readout scheme for AI edge devices","volume":"58","author":"Hung","year":"2023","journal-title":"IEEE J. Solid-State Circuits"}],"container-title":["IEEE Transactions on Circuits and Systems I: Regular Papers"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/8919\/10768429\/10736625.pdf?arnumber=10736625","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,27]],"date-time":"2024-11-27T09:08:59Z","timestamp":1732698539000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10736625\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12]]},"references-count":39,"journal-issue":{"issue":"12"},"URL":"https:\/\/doi.org\/10.1109\/tcsi.2024.3480154","relation":{},"ISSN":["1549-8328","1558-0806"],"issn-type":[{"type":"print","value":"1549-8328"},{"type":"electronic","value":"1558-0806"}],"subject":[],"published":{"date-parts":[[2024,12]]}}}