{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,30]],"date-time":"2025-07-30T16:38:39Z","timestamp":1753893519748,"version":"3.41.2"},"reference-count":38,"publisher":"American Association for the Advancement of Science (AAAS)","content-domain":{"domain":["spj.science.org"],"crossmark-restriction":true},"short-container-title":["Intell Comput"],"published-print":{"date-parts":[[2024,1]]},"abstract":"<jats:p>Optical neural networks (ONNs) have recently attracted extensive interest as potential alternatives to electronic artificial neural networks, owing to their intrinsic capabilities in parallel signal processing with reduced power consumption and low latency. Preliminary confirmation of parallelism in optical computing has been widely performed by applying wavelength division multiplexing (WDM) to the linear transformation of neural networks. However, interchannel crosstalk has obstructed WDM technologies from being deployed in nonlinear activation on ONNs. Here, we propose a universal WDM structure called multiplexed neuron sets (MNS), which applies WDM technologies to optical neurons and enables ONNs to be further compressed. A corresponding backpropagation (BP) training algorithm was proposed to alleviate or even annul the influence of interchannel crosstalk in MNS-based WDM-ONNs. For simplicity, semiconductor optical amplifiers are employed as an example of MNS to construct a WDM-ONN trained using the new algorithm. The results show that the combination of MNS and the corresponding BP training algorithm clearly downsizes the system and improves the energy efficiency by a factor of 10 while providing similar performance to traditional ONNs.<\/jats:p>","DOI":"10.34133\/icomputing.0070","type":"journal-article","created":{"date-parts":[[2023,12,18]],"date-time":"2023-12-18T10:49:13Z","timestamp":1702896553000},"update-policy":"https:\/\/doi.org\/10.34133\/aaas_crossmark_01","source":"Crossref","is-referenced-by-count":0,"title":["Slimmed Optical Neural Networks with Multiplexed Neuron Sets and a Corresponding Backpropagation Training Algorithm"],"prefix":"10.34133","volume":"3","author":[{"given":"Yi-Feng","family":"Liu","sequence":"first","affiliation":[{"name":"College of Information Science and Electronic Engineering, \rZhejiang University, Hangzhou 310027, China."},{"name":"State Key Laboratory of Extreme Photonics and Instrumentation, \rZhejiang University, Hangzhou 310027, China."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rui-Yao","family":"Ren","sequence":"additional","affiliation":[{"name":"College of Information Science and Electronic Engineering, \rZhejiang University, Hangzhou 310027, China."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dai-Bao","family":"Hou","sequence":"additional","affiliation":[{"name":"College of Information Science and Electronic Engineering, \rZhejiang University, Hangzhou 310027, China."},{"name":"State Key Laboratory of Extreme Photonics and Instrumentation, \rZhejiang University, Hangzhou 310027, China."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hai-Zhong","family":"Weng","sequence":"additional","affiliation":[{"name":"School of Physics, CRANN and AMBER, \rTrinity College Dublin, Dublin 2, Ireland."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bo-Wen","family":"Wang","sequence":"additional","affiliation":[{"name":"Synopsys, Inc., 7521PL Enschede, the Netherlands."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ke-Jie","family":"Huang","sequence":"additional","affiliation":[{"name":"College of Information Science and Electronic Engineering, \rZhejiang University, Hangzhou 310027, China."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xing","family":"Lin","sequence":"additional","affiliation":[{"name":"College of Information Science and Electronic Engineering, \rZhejiang University, Hangzhou 310027, China."},{"name":"State Key Laboratory of Extreme Photonics and Instrumentation, \rZhejiang University, Hangzhou 310027, China."},{"name":"Interdisciplinary Center for Quantum Information, \rZhejiang University, Hangzhou 310027, China."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Feng","family":"Liu","sequence":"additional","affiliation":[{"name":"College of Information Science and Electronic Engineering, \rZhejiang University, Hangzhou 310027, China."},{"name":"State Key Laboratory of Extreme Photonics and Instrumentation, \rZhejiang University, Hangzhou 310027, China."},{"name":"Interdisciplinary Center for Quantum Information, \rZhejiang University, Hangzhou 310027, China."},{"name":"International Joint Innovation Center, \rZhejiang University, Haining 314400, China."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chen-Hui","family":"Li","sequence":"additional","affiliation":[{"name":"College of Information Science and Electronic Engineering, \rZhejiang University, Hangzhou 310027, China."},{"name":"Zhejiang Lab, Hangzhou 311121, China."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2656-2397","authenticated-orcid":true,"given":"Chao-Yuan","family":"Jin","sequence":"additional","affiliation":[{"name":"College of Information Science and Electronic Engineering, \rZhejiang University, Hangzhou 310027, China."},{"name":"State Key Laboratory of Extreme Photonics and Instrumentation, \rZhejiang University, Hangzhou 310027, China."},{"name":"Interdisciplinary Center for Quantum Information, \rZhejiang University, Hangzhou 310027, China."},{"name":"International Joint Innovation Center, \rZhejiang University, Haining 314400, China."},{"name":"Center for Information Technology Application Innovation, Shaoxing Institute, \rZhejiang University, Shaoxing 312000, China."}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"221","published-online":{"date-parts":[[2024,2,20]]},"reference":[{"key":"e_1_3_4_2_2","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"e_1_3_4_3_2","doi-asserted-by":"publisher","DOI":"10.1038\/nature24270"},{"key":"e_1_3_4_4_2","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-018-0337-2"},{"key":"e_1_3_4_5_2","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2957245"},{"key":"e_1_3_4_6_2","doi-asserted-by":"crossref","DOI":"10.1016\/j.optlastec.2020.106787","article-title":"A survey of approaches for implementing optical neural networks","volume":"136","author":"Xu R","year":"2021","unstructured":"Xu R, Lv P, Xu F, Shi Y. A survey of approaches for implementing optical neural networks. Opt Laser Technol. 2021;136: Article 106787.","journal-title":"Opt Laser Technol"},{"key":"e_1_3_4_7_2","doi-asserted-by":"publisher","DOI":"10.1038\/s41566-020-00754-y"},{"issue":"1","key":"e_1_3_4_8_2","first-page":"1981155","article-title":"Prospects and applications of photonic neural networks","volume":"7","author":"Huang C","year":"2022","unstructured":"Huang C, Sorger VJ, Miscuglio M, al-Qadasi M, Mukherjee A, Lampe L, Nichols M, Tait AN, Ferreira de Lima T, Marquez BA, et al. Prospects and applications of photonic neural networks. Adv Phys X. 2022;7(1):1981155.","journal-title":"Adv Phys X"},{"key":"e_1_3_4_9_2","doi-asserted-by":"crossref","first-page":"30","DOI":"10.1038\/s41377-022-00717-8","article-title":"Photonic matrix multiplication lights up photonic accelerator and beyond","volume":"11","author":"Zhou H","year":"2022","unstructured":"Zhou H, Dong J, Cheng J, Dong W, Huang C, Shen Y, Zhang Q, Gu M, Qian C, Chen H, et al. Photonic matrix multiplication lights up photonic accelerator and beyond. Light Sci Appl. 2022;11:30.","journal-title":"Light Sci Appl"},{"key":"e_1_3_4_10_2","doi-asserted-by":"publisher","DOI":"10.1038\/nphoton.2017.93"},{"key":"e_1_3_4_11_2","doi-asserted-by":"crossref","DOI":"10.1186\/s43074-021-00026-0","article-title":"Research progress in optical neural networks: Theory, applications and developments","volume":"2","author":"Liu J","year":"2021","unstructured":"Liu J, Wu Q, Sui X, Chen Q, Gu G, Wang L, Li S. Research progress in optical neural networks: Theory, applications and developments. PhotoniX. 2021;2: Article 5.","journal-title":"PhotoniX"},{"key":"e_1_3_4_12_2","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.2987333"},{"issue":"10","key":"e_1_3_4_13_2","doi-asserted-by":"crossref","first-page":"1469","DOI":"10.1364\/AO.24.001469","article-title":"Optical implementation of the Hopfield model","volume":"24","author":"Farhat NH","year":"1985","unstructured":"Farhat NH, Psaltis D, Prata A, Paek E. Optical implementation of the Hopfield model. Appl Opt. 1985;24(10):1469\u20131475.","journal-title":"Appl Opt"},{"issue":"29","key":"e_1_3_4_14_2","doi-asserted-by":"crossref","first-page":"5367","DOI":"10.1364\/AO.39.005367","article-title":"Planar-integrated optical vector-matrix multiplier","volume":"39","author":"Gruber M","year":"2000","unstructured":"Gruber M, Jahns J, Sinzinger S. Planar-integrated optical vector-matrix multiplier. Appl Opt. 2000;39(29):5367\u20135373.","journal-title":"Appl Opt"},{"key":"e_1_3_4_15_2","doi-asserted-by":"publisher","DOI":"10.1126\/science.aat8084"},{"key":"e_1_3_4_16_2","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-020-20719-7"},{"key":"e_1_3_4_17_2","doi-asserted-by":"publisher","DOI":"10.1038\/s41377-020-0303-2"},{"issue":"7755","key":"e_1_3_4_18_2","doi-asserted-by":"crossref","first-page":"208","DOI":"10.1038\/s41586-019-1157-8","article-title":"All-optical spiking neurosynaptic networks with self-learning capabilities","volume":"569","author":"Feldmann J","year":"2019","unstructured":"Feldmann J, Youngblood N, Wright CD, Bhaskaran H, Pernice WH. All-optical spiking neurosynaptic networks with self-learning capabilities. Nature. 2019;569(7755):208\u2013214.","journal-title":"Nature"},{"key":"e_1_3_4_19_2","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-021-27774-8"},{"key":"e_1_3_4_20_2","doi-asserted-by":"publisher","DOI":"10.1126\/sciadv.adg4391"},{"key":"e_1_3_4_21_2","doi-asserted-by":"crossref","unstructured":"Ishihara T Shiomi J Hattori N Masuda Y Shinya A Notomi M. An optical neural network architecture based on highly parallelized WDM-multiplier-accumulator. Paper presented at: 2019 IEEE\/ACM Workshop on Photonics-Optics Technology Oriented Networking Information and Computing Systems; 2019 Nov 18; Denver CO.","DOI":"10.1109\/PHOTONICS49561.2019.00008"},{"key":"e_1_3_4_22_2","doi-asserted-by":"crossref","DOI":"10.1038\/s41598-022-09370-y","article-title":"Programmable photonic neural networks combining WDM with coherent linear optics","volume":"12","author":"Totovic A","year":"2022","unstructured":"Totovic A, Giamougiannis G, Tsakyridis A, Lazovsky D, Pleros N. Programmable photonic neural networks combining WDM with coherent linear optics. Sci Rep. 2022;12: Article 5605.","journal-title":"Sci Rep"},{"issue":"5","key":"e_1_3_4_23_2","doi-asserted-by":"crossref","DOI":"10.1109\/JSTQE.2020.2995830","article-title":"All-optical WDM recurrent neural networks with gating","volume":"26","author":"Mourgias-Alexandris G","year":"2020","unstructured":"Mourgias-Alexandris G, Dabos G, Passalis N, Totovic A, Tefas A, Pleros N. All-optical WDM recurrent neural networks with gating. IEEE J Sel Top Quantum Electron. 2020;26(5): Article 6100907.","journal-title":"IEEE J Sel Top Quantum Electron"},{"issue":"1","key":"e_1_3_4_24_2","article-title":"Deep neural network through an InP SOA-based photonic integrated cross-connect","volume":"26","author":"Shi B","year":"2019","unstructured":"Shi B, Calabretta N, Stabile R. Deep neural network through an InP SOA-based photonic integrated cross-connect. IEEE J Sel Top Quantum Electron. 2019;26(1): Article 7701111.","journal-title":"IEEE J Sel Top Quantum Electron"},{"key":"e_1_3_4_25_2","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-020-03070-1"},{"key":"e_1_3_4_26_2","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-020-03063-0"},{"key":"e_1_3_4_27_2","doi-asserted-by":"publisher","DOI":"10.1038\/s41928-021-00661-2"},{"issue":"6","key":"e_1_3_4_28_2","article-title":"Microring weight banks","volume":"22","author":"Tait AN","year":"2016","unstructured":"Tait AN, Wu AX, de Lima TF, Zhou E, Shastri BJ, Nahmias MA, Prucnal PR. Microring weight banks. IEEE J Sel Top Quantum Electron. 2016;22(6): Article 5900214.","journal-title":"IEEE J Sel Top Quantum Electron"},{"key":"e_1_3_4_29_2","doi-asserted-by":"crossref","unstructured":"Zhao Z Liu D Li M Ying Z Zhang L Xu B Yu B Chen RT Pan DZ Hardware-software co-design of slimmed optical neural networks. Paper presented at: Proceedings of the 24th Asia and South Pacific Design Automation Conference; 2019 Jan 21\u201324; Tokyo Japan.","DOI":"10.1145\/3287624.3287720"},{"key":"e_1_3_4_30_2","first-page":"3531","article-title":"Metasurface on integrated photonic platform: From mode converters to machine learning","volume":"11","author":"Wang Z","year":"2022","unstructured":"Wang Z, Xiao Y, Liao K, Li T, Song H, Chen H, Uddin SMZ, Mao D, Wang F, Zhou Z, et al. Metasurface on integrated photonic platform: From mode converters to machine learning. Nano. 2022;11:3531.","journal-title":"Nano"},{"issue":"1","key":"e_1_3_4_31_2","doi-asserted-by":"crossref","first-page":"1044","DOI":"10.1038\/s41467-022-28702-0","article-title":"Space-efficient optical computing with an integrated chip diffractive neural network","volume":"13","author":"Zhu H","year":"2022","unstructured":"Zhu H, Zou J, Zhang H, Shi YZ, Luo SB, Wang N, Cai H, Wan LX, Wang B, Jiang XD, et al. Space-efficient optical computing with an integrated chip diffractive neural network. Nat Commun. 2022;13(1):1044.","journal-title":"Nat Commun"},{"key":"e_1_3_4_32_2","article-title":"Silicon photonic modulator neuron","volume":"11","author":"Tait AN","year":"2019","unstructured":"Tait AN, Ferreira de Lima T, Nahmias MA, Miller HB, Peng HT, Shastri BJ, Prucnal PR. Silicon photonic modulator neuron. Phys Rev Applied. 2019;11: Article 064043.","journal-title":"Phys Rev Applied"},{"issue":"1","key":"e_1_3_4_33_2","article-title":"Reprogrammable electro-optic nonlinear activation functions for optical neural networks","volume":"26","author":"Williamson IA","year":"2019","unstructured":"Williamson IA, Hughes TW, Minkov M, Bartlett B, Pai S, Fan S. Reprogrammable electro-optic nonlinear activation functions for optical neural networks. IEEE J Sel Top Quantum Electron. 2019;26(1): Article 7700412.","journal-title":"IEEE J Sel Top Quantum Electron"},{"issue":"8","key":"e_1_3_4_34_2","doi-asserted-by":"crossref","DOI":"10.1063\/1.5109039","article-title":"Ito-based electro-absorption modulator for photonic neural activation function","volume":"7","author":"Amin R","year":"2019","unstructured":"Amin R, George JK, Sun S, Ferreira de Lima T, Tait AN, Khurgin JB, Miscuglio M, Shastri BJ, Prucnal PR, el-Ghazawi T, et al. Ito-based electro-absorption modulator for photonic neural activation function. APL Mater. 2019;7(8): Article 081112.","journal-title":"APL Mater"},{"issue":"1","key":"e_1_3_4_35_2","article-title":"InP photonic integrated multi-layer neural networks: Architecture and performance analysis","volume":"7","author":"Shi B","year":"2022","unstructured":"Shi B, Calabretta N, Stabile R. InP photonic integrated multi-layer neural networks: Architecture and performance analysis. APL Photonics. 2022;7(1): Article 010801.","journal-title":"APL Photonics"},{"key":"e_1_3_4_36_2","doi-asserted-by":"publisher","DOI":"10.1364\/OE.27.009620"},{"key":"e_1_3_4_37_2","doi-asserted-by":"publisher","DOI":"10.1002\/lpor.202000070"},{"key":"e_1_3_4_38_2","unstructured":"Xiao H Rasul K Vollgraf R. Fashion-mnist: A novel image dataset for benchmarking machine learning algorithms. arXiv. 2017. https:\/\/arxiv.org\/abs\/1708.07747"},{"issue":"6","key":"e_1_3_4_39_2","doi-asserted-by":"crossref","first-page":"141","DOI":"10.1109\/MSP.2012.2211477","article-title":"The MNIST database of handwritten digit images for machine learning research [best of the web]","volume":"29","author":"Deng L","year":"2012","unstructured":"Deng L. The MNIST database of handwritten digit images for machine learning research [best of the web]. IEEE Signal Process Mag. 2012;29(6):141\u2013142.","journal-title":"IEEE Signal Process Mag"}],"container-title":["Intelligent Computing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/spj.science.org\/doi\/pdf\/10.34133\/icomputing.0070","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,21]],"date-time":"2024-02-21T07:39:53Z","timestamp":1708501193000},"score":1,"resource":{"primary":{"URL":"https:\/\/spj.science.org\/doi\/10.34133\/icomputing.0070"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,1]]},"references-count":38,"alternative-id":["10.34133\/icomputing.0070"],"URL":"https:\/\/doi.org\/10.34133\/icomputing.0070","relation":{},"ISSN":["2771-5892"],"issn-type":[{"type":"electronic","value":"2771-5892"}],"subject":[],"published":{"date-parts":[[2024,1]]},"assertion":[{"value":"2023-08-23","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2023-11-18","order":1,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2024-02-20","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"0070"}}