{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T04:18:39Z","timestamp":1750220319723,"version":"3.41.0"},"reference-count":66,"publisher":"Association for Computing Machinery (ACM)","issue":"2","license":[{"start":{"date-parts":[[2022,3,10]],"date-time":"2022-03-10T00:00:00Z","timestamp":1646870400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["J. Emerg. Technol. Comput. Syst."],"published-print":{"date-parts":[[2022,4,30]]},"abstract":"<jats:p>\n            This work addresses how to naturally adopt the\n            <jats:italic>l<\/jats:italic>\n            <jats:sup>2<\/jats:sup>\n            -norm cosine similarity in the neuromemristive system and studies the unsupervised learning performance on handwritten digit image recognition. Proposed architecture is a two-layer fully connected neural network with a hard winner-take-all (WTA) learning module. For input layer, we propose single-spike temporal code that transforms input stimuli into the set of single spikes with different latencies and voltage levels. For a synapse model, we employ a compound memristor where stochastically switching binary-state memristors connected in parallel, which offers a reliable and scalable multi-state solution for synaptic weight storage. Hardware-friendly synaptic adaptation mechanism is proposed to realize spike-timing-dependent plasticity learning. Input spikes are sent out through those memristive synapses to each and every integrate-and-fire neuron in the fully connected output layer, where the hard WTA network motif introduces the competition based on cosine similarity for the given input stimuli. Finally, we present 92.64% accuracy performance on unsupervised digit recognition with only single-epoch MNIST dataset training via high-level simulations, including extensive analysis on the impact of system parameters.\n          <\/jats:p>","DOI":"10.1145\/3473036","type":"journal-article","created":{"date-parts":[[2022,3,10]],"date-time":"2022-03-10T14:06:32Z","timestamp":1646921192000},"page":"1-20","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["Unsupervised Digit Recognition Using Cosine Similarity In A Neuromemristive Competitive Learning System"],"prefix":"10.1145","volume":"18","author":[{"given":"Bon Woong","family":"Ku","sequence":"first","affiliation":[{"name":"Synopsys, Inc., Sunnyvale, CA"}]},{"given":"Catherine D.","family":"Schuman","sequence":"additional","affiliation":[{"name":"Oak Ridge National Laboratory, Oak Ridge, TN"}]},{"given":"Md Musabbir","family":"Adnan","sequence":"additional","affiliation":[{"name":"The University of Tennessee, Knoxville, TN"}]},{"given":"Tiffany M.","family":"Mintz","sequence":"additional","affiliation":[{"name":"Oak Ridge National Laboratory, Oak Ridge, TN"}]},{"given":"Raphael","family":"Pooser","sequence":"additional","affiliation":[{"name":"Oak Ridge National Laboratory, Oak Ridge, TN"}]},{"given":"Kathleen E.","family":"Hamilton","sequence":"additional","affiliation":[{"name":"Oak Ridge National Laboratory, Oak Ridge, TN"}]},{"given":"Garrett S.","family":"Rose","sequence":"additional","affiliation":[{"name":"The University of Tennessee, Knoxville, TN"}]},{"given":"Sung Kyu","family":"Lim","sequence":"additional","affiliation":[{"name":"Georgia Institute of Technology, Atlanta, GA"}]}],"member":"320","published-online":{"date-parts":[[2022,3,10]]},"reference":[{"key":"e_1_3_1_2_2","doi-asserted-by":"publisher","DOI":"10.1109\/TED.2016.2630925"},{"key":"e_1_3_1_3_2","doi-asserted-by":"publisher","DOI":"10.1113\/jphysiol.1926.sp002273"},{"key":"e_1_3_1_4_2","doi-asserted-by":"publisher","DOI":"10.1109\/JETCAS.2015.2435512"},{"key":"e_1_3_1_5_2","doi-asserted-by":"publisher","DOI":"10.1049\/el.2015.3807"},{"key":"e_1_3_1_6_2","doi-asserted-by":"publisher","DOI":"10.1109\/IEDM.2011.6131654"},{"key":"e_1_3_1_7_2","doi-asserted-by":"publisher","DOI":"10.3389\/fnins.2014.00412"},{"key":"e_1_3_1_8_2","doi-asserted-by":"publisher","DOI":"10.3389\/fnsys.2015.00151"},{"key":"e_1_3_1_9_2","doi-asserted-by":"publisher","DOI":"10.1080\/23746149.2016.1259585"},{"key":"e_1_3_1_10_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.sse.2016.07.006"},{"key":"e_1_3_1_11_2","doi-asserted-by":"publisher","DOI":"10.1126\/science.174.4011.788"},{"key":"e_1_3_1_12_2","doi-asserted-by":"publisher","DOI":"10.3389\/fncom.2015.00099"},{"key":"e_1_3_1_13_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-45238-6_13"},{"key":"e_1_3_1_14_2","doi-asserted-by":"crossref","first-page":"763","DOI":"10.1007\/978-3-540-78293-3_18","volume-title":"Computational Intelligence: A Compendium","author":"Furber Steve","year":"2008","unstructured":"Steve Furber and Steve Temple. 2008. Neural systems engineering. In Computational Intelligence: A Compendium. Springer, 763\u2013796."},{"key":"e_1_3_1_15_2","doi-asserted-by":"publisher","DOI":"10.1126\/science.1149639"},{"key":"e_1_3_1_16_2","doi-asserted-by":"publisher","DOI":"10.1145\/3381755.3381770"},{"key":"e_1_3_1_17_2","first-page":"773","volume-title":"Advances in Neural Information Processing Systems","author":"Habenschuss Stefan","year":"2012","unstructured":"Stefan Habenschuss, Johannes Bill, and Bernhard Nessler. 2012. Homeostatic plasticity in Bayesian spiking networks as expectation maximization with posterior constraints. In Advances in Neural Information Processing Systems, Vol. 25. 773\u2013781."},{"key":"e_1_3_1_18_2","doi-asserted-by":"publisher","DOI":"10.1145\/3183584.3183622"},{"key":"e_1_3_1_19_2","doi-asserted-by":"publisher","DOI":"10.4324\/9781410612403"},{"key":"e_1_3_1_20_2","doi-asserted-by":"publisher","DOI":"10.1145\/2897937.2898010"},{"key":"e_1_3_1_21_2","doi-asserted-by":"publisher","DOI":"10.1021\/acs.nanolett.8b01526"},{"key":"e_1_3_1_22_2","doi-asserted-by":"publisher","DOI":"10.1021\/nl904092h"},{"key":"e_1_3_1_23_2","doi-asserted-by":"publisher","DOI":"10.1145\/3079856.3080246"},{"key":"e_1_3_1_24_2","volume-title":"Principles of Neural Science","author":"Kandel Eric R.","year":"2000","unstructured":"Eric R. Kandel et\u00a0al. 2000. Principles of Neural Science. Vol. 4. McGraw\u2013Hill, New York."},{"key":"e_1_3_1_25_2","doi-asserted-by":"publisher","DOI":"10.1016\/S0893-6080(05)80154-6"},{"key":"e_1_3_1_26_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2016.04.029"},{"key":"e_1_3_1_27_2","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2011.2166749"},{"key":"e_1_3_1_28_2","doi-asserted-by":"publisher","DOI":"10.1109\/SOCC.2012.6398336"},{"key":"e_1_3_1_29_2","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2019.2899262"},{"key":"e_1_3_1_30_2","doi-asserted-by":"publisher","DOI":"10.1126\/science.1089662"},{"key":"e_1_3_1_31_2","unstructured":"Yann LeCun. 1998. The MNIST Database of Handwritten Digits. Retrieved from http:\/\/yann.lecun.com\/exdb\/mnist\/."},{"key":"e_1_3_1_32_2","doi-asserted-by":"publisher","DOI":"10.1038\/ncomms15666"},{"key":"e_1_3_1_33_2","doi-asserted-by":"publisher","DOI":"10.1109\/DAC18072.2020.9218578"},{"key":"e_1_3_1_34_2","article-title":"A memristor based unsupervised neuromorphic system towards fast and energy-efficient GAN","author":"Liu F.","year":"2018","unstructured":"F. Liu and C. Liu. 2018. A memristor based unsupervised neuromorphic system towards fast and energy-efficient GAN. arXiv:1806.01775. Retrieved from https:\/\/arxiv.org\/abs\/1806.01775.","journal-title":"arXiv:1806.01775"},{"key":"e_1_3_1_35_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01418-6_38"},{"key":"e_1_3_1_36_2","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pcbi.0030031"},{"key":"e_1_3_1_37_2","doi-asserted-by":"publisher","DOI":"10.1109\/5.58356"},{"key":"e_1_3_1_38_2","doi-asserted-by":"publisher","DOI":"10.1186\/1556-276X-9-526"},{"key":"e_1_3_1_39_2","doi-asserted-by":"publisher","DOI":"10.1109\/MC.2016.312"},{"key":"e_1_3_1_40_2","doi-asserted-by":"publisher","DOI":"10.1109\/NAECON.2015.7443093"},{"key":"e_1_3_1_41_2","doi-asserted-by":"publisher","DOI":"10.1109\/TNANO.2015.2493960"},{"key":"e_1_3_1_42_2","article-title":"Evolving and understanding sparse deep neural networks using cosine similarity","author":"Pieterse Joost","year":"2019","unstructured":"Joost Pieterse and Decebal Constantin Mocanu. 2019. Evolving and understanding sparse deep neural networks using cosine similarity. arXiv:1903.07138. Retrieved from https:\/\/arxiv.org\/abs\/1903.07138.","journal-title":"arXiv:1903.07138"},{"key":"e_1_3_1_43_2","doi-asserted-by":"publisher","DOI":"10.1523\/JNEUROSCI.1792-08.2008"},{"key":"e_1_3_1_44_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2018.02.010"},{"key":"e_1_3_1_45_2","doi-asserted-by":"publisher","DOI":"10.1109\/TNANO.2013.2250995"},{"key":"e_1_3_1_46_2","doi-asserted-by":"publisher","DOI":"10.1523\/JNEUROSCI.20-14-05392.2000"},{"key":"e_1_3_1_47_2","article-title":"Regularizing cnns with locally constrained decorrelations","author":"Rodr\u00edguez Pau","year":"2016","unstructured":"Pau Rodr\u00edguez, Jordi Gonzalez, Guillem Cucurull, Josep M. Gonfaus, and Xavier Roca. 2016. Regularizing cnns with locally constrained decorrelations. arXiv:1611.01967. Retrieved from https:\/\/arxiv.org\/abs\/1611.01967.","journal-title":"arXiv:1611.01967"},{"key":"e_1_3_1_48_2","first-page":"67","volume-title":"Proceedings of the IEEE\/ACM International Symposium on Nanoscale Architectures (NANOARCH\u201916)","author":"Shahsavari Mahyar","year":"2016","unstructured":"Mahyar Shahsavari, Pierre Falez, and Pierre Boulet. 2016. Combining a volatile and nonvolatile memristor in artificial synapse to improve learning in spiking neural networks. In Proceedings of the IEEE\/ACM International Symposium on Nanoscale Architectures (NANOARCH\u201916). IEEE, 67\u201372."},{"key":"e_1_3_1_49_2","doi-asserted-by":"publisher","DOI":"10.1038\/scientificamerican0992-60"},{"key":"e_1_3_1_50_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2014.09.013"},{"key":"e_1_3_1_51_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISCAS.2014.6865326"},{"key":"e_1_3_1_52_2","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-018-07682-0"},{"key":"e_1_3_1_53_2","article-title":"Hebbian Learning Rules with Memristors","author":"Soudry Daniel","year":"2013","unstructured":"Daniel Soudry, Dotan Di Castro, Asaf Gal, Avinoam Kolodny, and Shahar Kvatinsky. 2013. Hebbian Learning Rules with Memristors. Israel Institute of Technology, Haifa, Israel.","journal-title":"Israel Institute of Technology, Haifa, Israel"},{"key":"e_1_3_1_54_2","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-017-17785-1"},{"key":"e_1_3_1_55_2","doi-asserted-by":"publisher","DOI":"10.1109\/81.915396"},{"key":"e_1_3_1_56_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISCAS.2010.5537020"},{"key":"e_1_3_1_57_2","doi-asserted-by":"publisher","DOI":"10.1152\/jn.1996.76.2.1310"},{"key":"e_1_3_1_58_2","first-page":"1058","volume-title":"Proceedings of the International Conference on Machine Learning","author":"Wan Li","year":"2013","unstructured":"Li Wan, Matthew Zeiler, Sixin Zhang, Yann Le Cun, and Rob Fergus. 2013. Regularization of neural networks using dropconnect. In Proceedings of the International Conference on Machine Learning. PMLR, 1058\u20131066."},{"key":"e_1_3_1_59_2","doi-asserted-by":"publisher","DOI":"10.1145\/3123266.3123359"},{"key":"e_1_3_1_60_2","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2016.7727302"},{"key":"e_1_3_1_61_2","doi-asserted-by":"publisher","DOI":"10.1109\/MSSC.2016.2546199"},{"key":"e_1_3_1_62_2","doi-asserted-by":"publisher","DOI":"10.1109\/IEDM.2011.6131572"},{"key":"e_1_3_1_63_2","doi-asserted-by":"publisher","DOI":"10.1109\/TCSI.2017.2729787"},{"key":"e_1_3_1_64_2","doi-asserted-by":"publisher","DOI":"10.3390\/electronics7120396"},{"key":"e_1_3_1_65_2","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2909295"},{"key":"e_1_3_1_66_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.mejo.2012.10.001"},{"key":"e_1_3_1_67_2","doi-asserted-by":"publisher","DOI":"10.1038\/s41928-017-0006-8"}],"container-title":["ACM Journal on Emerging Technologies in Computing Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3473036","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3473036","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T20:11:57Z","timestamp":1750191117000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3473036"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,3,10]]},"references-count":66,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2022,4,30]]}},"alternative-id":["10.1145\/3473036"],"URL":"https:\/\/doi.org\/10.1145\/3473036","relation":{},"ISSN":["1550-4832","1550-4840"],"issn-type":[{"type":"print","value":"1550-4832"},{"type":"electronic","value":"1550-4840"}],"subject":[],"published":{"date-parts":[[2022,3,10]]},"assertion":[{"value":"2020-08-01","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2021-06-01","order":1,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2022-03-10","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}