{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,4,16]],"date-time":"2025-04-16T02:48:54Z","timestamp":1744771734928},"reference-count":32,"publisher":"Institute of Electronics, Information and Communications Engineers (IEICE)","issue":"5","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEICE Electron. Express"],"published-print":{"date-parts":[[2019]]},"DOI":"10.1587\/elex.16.20190004","type":"journal-article","created":{"date-parts":[[2019,2,14]],"date-time":"2019-02-14T22:39:52Z","timestamp":1550183992000},"page":"20190004-20190004","source":"Crossref","is-referenced-by-count":9,"title":["Quaternary synapses network for memristor-based spiking convolutional neural networks"],"prefix":"10.1587","volume":"16","author":[{"given":"Sheng-Yang","family":"Sun","sequence":"first","affiliation":[{"name":"College of Electronic Science, National University of Defense Technology"}]},{"given":"Jiwei","family":"Li","sequence":"additional","affiliation":[{"name":"College of Electronic Science, National University of Defense Technology"}]},{"given":"Zhiwei","family":"Li","sequence":"additional","affiliation":[{"name":"College of Electronic Science, National University of Defense Technology"}]},{"given":"Husheng","family":"Liu","sequence":"additional","affiliation":[{"name":"College of Electronic Science, National University of Defense Technology"}]},{"given":"Haijun","family":"Liu","sequence":"additional","affiliation":[{"name":"College of Electronic Science, National University of Defense Technology"}]},{"given":"Qingjiang","family":"Li","sequence":"additional","affiliation":[{"name":"College of Electronic Science, National University of Defense Technology"}]}],"member":"532","reference":[{"key":"1","doi-asserted-by":"publisher","unstructured":"[1] A. Schmid: \u201cNeuromorphic microelectronics from devices to hardware systems and applications,\u201d NOLTA <b>7<\/b> (2016) 468 (DOI: 10.1587\/nolta.7.468).","DOI":"10.1587\/nolta.7.468"},{"key":"2","doi-asserted-by":"publisher","unstructured":"[2] Y. Chen, <i>et al.<\/i>: \u201cA novel memristor-based restricted Boltzmann machine for contrastive divergence,\u201d IEICE Electron. Express <b>15<\/b> (2018) 20171062 (DOI: 10.1587\/elex.15.20171062).","DOI":"10.1587\/elex.15.20171062"},{"key":"3","doi-asserted-by":"publisher","unstructured":"[3] C. D. James, <i>et al.<\/i>: \u201cA historical survey of algorithms and hardware architectures for neural-inspired and neuromorphic computing applications,\u201d Biologically Inspired Cognitive Architectures <b>19<\/b> (2017) 49 (DOI: 10.1016\/j.bica.2016.11.002).","DOI":"10.1016\/j.bica.2016.11.002"},{"key":"4","doi-asserted-by":"publisher","unstructured":"[4] Y. V. Pershin and M. Di Ventra: \u201cNeuromorphic, digital, and quantum computation with memory circuit elements,\u201d Proc. IEEE <b>100<\/b> (2012) 2071 (DOI: 10.1109\/JPROC.2011.2166369).","DOI":"10.1109\/JPROC.2011.2166369"},{"key":"5","unstructured":"[5] Y. Taur and T. H. Ning: <i>Fundamentals of Modern VLSI Devices<\/i> (Cambridge University Press, Cambridge, 1998)."},{"key":"6","doi-asserted-by":"publisher","unstructured":"[6] S. Park, <i>et al.<\/i>: \u201cNanoscale RRAM-based synaptic electronics: Toward a neuromorphic computing device,\u201d Nanotechnology <b>24<\/b> (2013) 384009 (DOI: 10.1088\/0957-4484\/24\/38\/384009).","DOI":"10.1088\/0957-4484\/24\/38\/384009"},{"key":"7","doi-asserted-by":"publisher","unstructured":"[7] B. C. Jang, <i>et al.<\/i>: \u201cMemristive logic-in-memory integrated circuits for energy-efficient flexible electronics,\u201d Adv. Funct. Mater. <b>28<\/b> (2018) 1704725 (DOI: 10.1002\/adfm.201704725).","DOI":"10.1002\/adfm.201704725"},{"key":"8","doi-asserted-by":"publisher","unstructured":"[8] A. Krizhevsky, <i>et al.<\/i>: \u201cImagenet classification with deep convolutional neural networks,\u201d NIPS. Curran Associates Inc. (2012) 1097 (DOI: 10.1145\/3065386).","DOI":"10.1145\/3065386"},{"key":"9","doi-asserted-by":"crossref","unstructured":"[9] D. Dang, <i>et al.<\/i>: \u201cConvLight: A convolutional accelerator with memristor integrated photonic computing,\u201d IEEE HiPC (2017) 114 (DOI: 10.1109\/HiPC.2017.00022).","DOI":"10.1109\/HiPC.2017.00022"},{"key":"10","doi-asserted-by":"crossref","unstructured":"[10] A. Ankit, <i>et al.<\/i>: \u201cTrannsformer: Neural network transformation for memristive crossbar based neuromorphic system design,\u201d IEEE ICCAD (2017) 533 (DOI: 10.1109\/ICCAD.2017.8203823).","DOI":"10.1109\/ICCAD.2017.8203823"},{"key":"11","unstructured":"[11] A. Ankit, <i>et al.<\/i>: \u201cResparc: A reconfigurable and energy-efficient architecture with memristive crossbars for deep spiking neural networks,\u201d ACM 54th Annual Design Automation Conference (2017) 27 (DOI: 10.1145\/3061639.3062311)."},{"key":"12","doi-asserted-by":"crossref","unstructured":"[12] S. Sun, <i>et al.<\/i>: \u201cLow-consumption neuromorphic memristor architecture based on convolutional neural networks,\u201d IEEE IJCNN (2018) 1 (DOI: 10.1109\/IJCNN.2018.8489441).","DOI":"10.1109\/IJCNN.2018.8489441"},{"key":"13","doi-asserted-by":"publisher","unstructured":"[13] X. Zhu, <i>et al.<\/i>: \u201cMulti-level programming of memristor in nanocrossbar,\u201d IEICE Electron. Express <b>10<\/b> (2013) 20130013 (DOI: 10.1587\/elex.10.20130013).","DOI":"10.1587\/elex.10.20130013"},{"key":"14","doi-asserted-by":"publisher","unstructured":"[14] Z. Li, <i>et al.<\/i>: \u201cDesign of ternary neural network with 3-D vertical RRAM array,\u201d IEEE Trans. Electron Devices <b>64<\/b> (2017) 2721 (DOI: 10.1109\/TED.2017.2697361).","DOI":"10.1109\/TED.2017.2697361"},{"key":"15","doi-asserted-by":"publisher","unstructured":"[15] G. W. Burr, <i>et al.<\/i>: \u201cExperimental demonstration and tolerancing of a large-scale neural network (165000 synapses) using phase-change memory as the synaptic weight element,\u201d IEEE Trans. Electron Devices <b>62<\/b> (2015) 3498 (DOI: 10.1109\/TED.2015.2439635).","DOI":"10.1109\/TED.2015.2439635"},{"key":"16","doi-asserted-by":"publisher","unstructured":"[16] Y. Sun, <i>et al.<\/i>: \u201cA Ti\/AlOx\/TaOx\/Pt analog synapse for memristive neural network,\u201d IEEE Electron Device Lett. <b>39<\/b> (2018) 1298 (DOI: 10.1109\/LED.2018.2860053).","DOI":"10.1109\/LED.2018.2860053"},{"key":"17","unstructured":"[17] H. Kim, <i>et al.<\/i>: \u201cMemristor-based multilevel memory,\u201d IEEE 12th international CNNA workshop (2010) 1 (DOI: 10.1109\/CNNA.2010.5430320)."},{"key":"18","doi-asserted-by":"publisher","unstructured":"[18] C. Soell, <i>et al.<\/i>: \u201cCase study on memristor-based multilevel memories,\u201d Int. J. Circuit Theory Appl. <b>46<\/b> (2018) 99 (DOI: 10.1002\/cta.2379).","DOI":"10.1002\/cta.2379"},{"key":"19","doi-asserted-by":"publisher","unstructured":"[19] Y. Sun, <i>et al.<\/i>: \u201cShort-term and long-term plasticity mimicked in low voltage Ag\/GeSe\/TiN electronic synapse,\u201d IEEE Electron Device Lett. <b>39<\/b> (2018) 492 (DOI: 10.1109\/LED.2018.2809784).","DOI":"10.1109\/LED.2018.2809784"},{"key":"20","doi-asserted-by":"publisher","unstructured":"[20] Y. L. Lecun, <i>et al.<\/i>: \u201cGradient-based learning applied to document recognition,\u201d Proc. IEEE <b>86<\/b> (1998) 2278 (DOI: 10.1109\/5.726791).","DOI":"10.1109\/5.726791"},{"key":"21","doi-asserted-by":"crossref","unstructured":"[21] C. Szegedy, <i>et al.<\/i>: \u201cGoing deeper with convolutions,\u201d Proc. IEEE Conf. Computer Vision and Pattern Recognition (2015) 1 (DOI: 10.1109\/CVPR.2015.7298594).","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"22","doi-asserted-by":"crossref","unstructured":"[22] K. He, <i>et al.<\/i>: \u201cDeep residual learning for image recognition,\u201d Proc. IEEE Conf. Computer Vision and Pattern Recognition (2016) 770 (DOI: 10.1109\/CVPR.2016.90).","DOI":"10.1109\/CVPR.2016.90"},{"key":"23","unstructured":"[23] K. Simonyan and A. Zisserman: \u201cVery deep convolutional networks for large-scale image recognition,\u201d arXiv:1409.1556 (2014)."},{"key":"24","doi-asserted-by":"crossref","unstructured":"[24] M. Hu, <i>et al.<\/i>: \u201cDot-product engine for neuromorphic computing: Programming 1T1M crossbar to accelerate matrix-vector multiplication,\u201d Proc. DAC <b>53<\/b> (2016) (DOI: 10.1145\/2897937.2898010).","DOI":"10.1145\/2897937.2898010"},{"key":"25","doi-asserted-by":"crossref","unstructured":"[25] S. C. Wong, <i>et al.<\/i>: \u201cUnderstanding data augmentation for classification: When to warp,\u201d arXiv:1609.08764 (2016).","DOI":"10.1109\/DICTA.2016.7797091"},{"key":"26","unstructured":"[26] L. Perez and J. Wang: \u201cThe effectiveness of data augmentation in image classification using deep learning,\u201d arXiv:1712.04621 (2017)."},{"key":"27","doi-asserted-by":"crossref","unstructured":"[27] R. Takahashi, <i>et al.<\/i>: \u201cData augmentation using random image cropping and patching for deep CNNs,\u201d arXiv:1811.09030 (2018).","DOI":"10.1109\/TCSVT.2019.2935128"},{"key":"28","unstructured":"[28] M. Courbariaux, <i>et al.<\/i>: \u201cBinaryconnect: Training deep neural networks with binary weights during propagations,\u201d Adv. Neural Inf. Process. Syst. (2015) 3123."},{"key":"29","unstructured":"[29] M. Courbariaux and Y. Bengio: \u201cBinaryNet: Training deep neural networks with weights and activations constrained to +1 or \u22121,\u201d arXiv:1602.02830 (2016)."},{"key":"30","doi-asserted-by":"publisher","unstructured":"[30] L. Deng, <i>et al.<\/i>: \u201cGated XNOR networks: Deep neural networks with ternary weights and activations under a unified discretization framework,\u201d Neural Netw. <b>100<\/b> (2017) 49 (DOI: 10.1016\/j.neunet.2018.01.010).","DOI":"10.1016\/j.neunet.2018.01.010"},{"key":"31","doi-asserted-by":"publisher","unstructured":"[31] F. Alibart, <i>et al.<\/i>: \u201cHigh precision tuning of state for memristive devices by adaptable variation-tolerant algorithm,\u201d Nanotechnology <b>23<\/b> (2012) 075201 (DOI: 10.1088\/0957-4484\/23\/7\/075201).","DOI":"10.1088\/0957-4484\/23\/7\/075201"},{"key":"32","doi-asserted-by":"crossref","unstructured":"[32] C. Yakopcic, <i>et al.<\/i>: \u201cExtremely parallel memristor crossbar architecture for convolutional neural network implementation,\u201d IEEE IJCNN (2017) 1696 (DOI: 10.1109\/IJCNN.2017.7966055).","DOI":"10.1109\/IJCNN.2017.7966055"}],"container-title":["IEICE Electronics Express"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.jstage.jst.go.jp\/article\/elex\/16\/5\/16_16.20190004\/_pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,11,17]],"date-time":"2019-11-17T02:23:03Z","timestamp":1573957383000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.jstage.jst.go.jp\/article\/elex\/16\/5\/16_16.20190004\/_article"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019]]},"references-count":32,"journal-issue":{"issue":"5","published-print":{"date-parts":[[2019]]}},"URL":"https:\/\/doi.org\/10.1587\/elex.16.20190004","relation":{},"ISSN":["1349-2543"],"issn-type":[{"value":"1349-2543","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019]]}}}