{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,19]],"date-time":"2026-06-19T15:50:10Z","timestamp":1781884210578,"version":"3.54.5"},"reference-count":64,"publisher":"Springer Science and Business Media LLC","issue":"29","license":[{"start":{"date-parts":[[2023,8,5]],"date-time":"2023-08-05T00:00:00Z","timestamp":1691193600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2023,8,5]],"date-time":"2023-08-05T00:00:00Z","timestamp":1691193600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/100010667","name":"H2020 Industrial Leadership","doi-asserted-by":"publisher","award":["871391"],"award-info":[{"award-number":["871391"]}],"id":[{"id":"10.13039\/100010667","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100006470","name":"Aristotle University of Thessaloniki","doi-asserted-by":"crossref","id":[{"id":"10.13039\/501100006470","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Neural Comput &amp; Applic"],"published-print":{"date-parts":[[2023,10]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:p>The energy demanding nature of deep learning (DL) has fueled the immense attention for neuromorphic architectures due to their ability to operate in a very high frequencies in a very low energy consumption. To this end, neuromorphic photonics are among the most promising research directions, since they are able to achieve femtojoule per MAC efficiency. Although electrooptical substances provide a fast and efficient platform for DL, they also introduce various noise sources that impact the effective bit resolution, introducing new challenges to DL quantization. In this work, we propose a quantization-aware training method that gradually performs bit reduction to layers in a mixed-precision manner, enabling us to operate lower-precision networks during deployment and further increase the computational rate of the developed accelerators while keeping the energy consumption low. Exploiting the observation that intermediate layers have lower-precision requirements, we propose to gradually reduce layers\u2019 bit resolutions, by normally distributing the reduction probability of each layer. We experimentally demonstrate the advantages of mixed-precision quantization in both performance and inference time. Furthermore, we experimentally evaluate the proposed method in different tasks, architectures, and photonic configurations, highlighting its immense capabilities to reduce the average bit resolution of DL models while significantly outperforming the evaluated baselines.<\/jats:p>","DOI":"10.1007\/s00521-023-08848-8","type":"journal-article","created":{"date-parts":[[2023,8,5]],"date-time":"2023-08-05T09:01:31Z","timestamp":1691226091000},"page":"21361-21379","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":21,"title":["Mixed-precision quantization-aware training for photonic neural networks"],"prefix":"10.1007","volume":"35","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8670-0248","authenticated-orcid":false,"given":"Manos","family":"Kirtas","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Nikolaos","family":"Passalis","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Athina","family":"Oikonomou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Miltos","family":"Moralis-Pegios","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"George","family":"Giamougiannis","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Apostolos","family":"Tsakyridis","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"George","family":"Mourgias-Alexandris","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Nikolaos","family":"Pleros","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Anastasios","family":"Tefas","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2023,8,5]]},"reference":[{"issue":"7553","key":"8848_CR1","doi-asserted-by":"publisher","first-page":"436","DOI":"10.1038\/nature14539","volume":"521","author":"Y LeCun","year":"2015","unstructured":"LeCun Y, Bengio Y, Hinton G (2015) Deep learning. Nature 521(7553):436\u2013444","journal-title":"Nature"},{"key":"8848_CR2","doi-asserted-by":"publisher","unstructured":"Brown TB, Mann B, Ryder N, Subbiah M, Kaplan J, Dhariwal P, Neelakantan A, Shyam P, Sastry G, Askell A, Agarwal S, Herbert-Voss A, Krueger G, Henighan T, Child R, Ramesh A, Ziegler DM, Wu J, Winter C, Hesse C, Chen M, Sigler E, Litwin M, Gray S, Chess B, Clark J, Berner C, McCandlish S, Radford A, Sutskever I, Amodei D (2020) Language models are few-shot learners. https:\/\/doi.org\/10.48550\/ARXIV.2005.14165. arXiv:org\/abs\/2005.14165","DOI":"10.48550\/ARXIV.2005.14165"},{"key":"8848_CR3","doi-asserted-by":"publisher","unstructured":"Ramesh A, Pavlov M, Goh G, Gray S, Voss C, Radford A, Chen M, Sutskever I (2021) Zero-shot text-to-image generation. https:\/\/doi.org\/10.48550\/ARXIV.2102.12092. arXiv:org\/abs\/2102.12092","DOI":"10.48550\/ARXIV.2102.12092"},{"key":"8848_CR4","doi-asserted-by":"publisher","unstructured":"Vaswani A, Shazeer N, Parmar N, Uszkoreit J, Jones L, Gomez AN, Kaiser L, Polosukhin I (2017) Attention is all you need. https:\/\/doi.org\/10.48550\/ARXIV.1706.03762. arXiv:org\/abs\/1706.03762","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"8848_CR5","doi-asserted-by":"publisher","unstructured":"Silver D, Hubert T, Schrittwieser J, Antonoglou I, Lai M, Guez A, Lanctot M, Sifre L, Kumaran D, Graepel T, Lillicrap T, Simonyan K, Hassabis D (2017) Mastering chess and shogi by self-play with a general reinforcement learning algorithm. https:\/\/doi.org\/10.48550\/ARXIV.1712.01815. arXiv:org\/abs\/1712.01815","DOI":"10.48550\/ARXIV.1712.01815"},{"issue":"5","key":"8848_CR6","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/JSTQE.2020.2975579","volume":"26","author":"AR Totovi\u0107","year":"2020","unstructured":"Totovi\u0107 AR, Dabos G, Passalis N, Tefas A, Pleros N (2020) Femtojoule per mac neuromorphic photonics: an energy and technology roadmap. IEEE J Sel Top Quantum Electron 26(5):1\u201315. https:\/\/doi.org\/10.1109\/JSTQE.2020.2975579","journal-title":"IEEE J Sel Top Quantum Electron"},{"key":"8848_CR7","doi-asserted-by":"publisher","unstructured":"Pleros N, Moralis-Pegios M, Totovic A, Dabos G, Tsakyridis A, Giamougiannis G, Mourgias-Alexandris G, Passalis N, Kirtas M, Tefas A (2021) Compute with light: architectures, technologies and training models for neuromorphic photonic circuits. In: 2021 european conference on optical communication (ECOC), pp 1\u20134. https:\/\/doi.org\/10.1109\/ECOC52684.2021.9606046","DOI":"10.1109\/ECOC52684.2021.9606046"},{"key":"8848_CR8","doi-asserted-by":"crossref","unstructured":"Moralis-Pegios M, Totovic A, Tsakyridis A, Giamougiannis G, Mourgias-Alexandris G, Dabos G, Passalis N, Kirtas M, Tefas A, Pleros N (2022) Photonic neuromorphic computing: architectures, technologies, and training models. In: 2022 optical fiber communications conference and exhibition (OFC), pp 01\u201303","DOI":"10.1364\/OFC.2022.M1G.4"},{"issue":"6406","key":"8848_CR9","doi-asserted-by":"publisher","first-page":"1004","DOI":"10.1126\/science.aat8084","volume":"361","author":"X Lin","year":"2018","unstructured":"Lin X, Rivenson Y, Yardimci NT, Veli M, Luo Y, Jarrahi M, Ozcan A (2018) All-optical machine learning using diffractive deep neural networks. Science 361(6406):1004\u20131008","journal-title":"Science"},{"issue":"7","key":"8848_CR10","doi-asserted-by":"publisher","first-page":"441","DOI":"10.1038\/nphoton.2017.93","volume":"11","author":"Y Shen","year":"2017","unstructured":"Shen Y, Harris NC, Skirlo S, Prabhu M, Baehr-Jones T, Hochberg M, Sun X, Zhao S, Larochelle H, Englund D et al (2017) Deep learning with coherent nanophotonic circuits. Nat Photonics 11(7):441","journal-title":"Nat Photonics"},{"issue":"2","key":"8848_CR11","doi-asserted-by":"publisher","DOI":"10.1088\/2634-4386\/ac724d","volume":"2","author":"A Totovic","year":"2022","unstructured":"Totovic A, Pappas C, Kirtas M, Tsakyridis A, Giamougiannis G, Passalis N, Moralis-Pegios M, Tefas A, Pleros N (2022) Wdm equipped universal linear optics for programmable neuromorphic photonic processors. Neuromorphic Comput Eng 2(2):024010","journal-title":"Neuromorphic Comput Eng"},{"key":"8848_CR12","doi-asserted-by":"publisher","unstructured":"Giamougiannis G, Tsakyridis A, Mourgias-Alexandris G, Moralis-Pegios M, Totovic A, Dabos G, Passalis N, Kirtas M, Bamiedakis N, Tefas A, Lazovsky D, Pleros N (2021) Silicon-integrated coherent neurons with 32gmac\/sec\/axon compute line-rates using eam-based input and weighting cells. In: 2021 European conference on optical communication (ECOC), pp 1\u20134 https:\/\/doi.org\/10.1109\/ECOC52684.2021.9605987","DOI":"10.1109\/ECOC52684.2021.9605987"},{"key":"8848_CR13","doi-asserted-by":"publisher","unstructured":"Mourgias-Alexandris G, Moralis-Pegios M, Simos S, Dabos G, Passalis N, Kirtas M, Rutirawut T, Gardes FY, Tefas A, Pleros N (2021) A silicon photonic coherent neuron with 10gmac\/sec processing line-rate. In: Optical fiber communication conference (OFC) 2021, pp 5\u20131. Optica Publishing Group, https:\/\/doi.org\/10.1364\/OFC.2021.Tu5H.1. https:\/\/opg.optica.org\/abstract.cfm?URI=OFC-2021-Tu5H.1","DOI":"10.1364\/OFC.2021.Tu5H.1"},{"key":"8848_CR14","doi-asserted-by":"crossref","unstructured":"Tsakyridis A, Giamougiannis G, Mourgias-Alexandris G, Totovic A, Dabos G, Passalis N, Kirtas M, Tefas A, Moralis-Pegios M, Pleros N (2022) Silicon photonic neuromorphic computing with 16 ghz input data and weight update line rates. In: 2022 conference on lasers and electro-optics (CLEO), pp 1\u20132","DOI":"10.1109\/JSTQE.2022.3228318"},{"key":"8848_CR15","doi-asserted-by":"publisher","unstructured":"Tsakyridis A, Giamougiannis G, Moralis-Pegios M, Mourgias-Alexandris G, Totovic AR, Kirtas M, Passalis N, Lazovsky D, Tefas A, Pleros N (2022) Universal linear optics for ultra-fast neuromorphic silicon photonics towards fj\/mac and tmac\/sec\/mm2 engines. IEEE J Sel Top Quantum Electron 28(6: High Density Integr. Multipurpose Photon. Circ.,pp  1\u201315 https:\/\/doi.org\/10.1109\/JSTQE.2022.3219288","DOI":"10.1109\/JSTQE.2022.3219288"},{"key":"8848_CR16","doi-asserted-by":"publisher","unstructured":"Kirtas M, Passalis N, Mourgias-Alexandris G, Dabos G, Pleros N, Tefas A (2022) Learning photonic neural network initialization for noise-aware end-to-end fiber transmission. In: 2022 30th European signal processing conference (EUSIPCO), pp 1731\u20131735. https:\/\/doi.org\/10.23919\/EUSIPCO55093.2022.9909781","DOI":"10.23919\/EUSIPCO55093.2022.9909781"},{"key":"8848_CR17","doi-asserted-by":"publisher","unstructured":"Kirtas M, Passalis N, Kalavrouziotis D, Syrivelis D, Bakopoulos P, Pleros N, Tefas A (2022) Early detection of ddos attacks using photonic neural networks. In: 2022 IEEE 14th image, video, and multidimensional signal processing workshop (IVMSP), pp 1\u20135 https:\/\/doi.org\/10.1109\/IVMSP54334.2022.9816178","DOI":"10.1109\/IVMSP54334.2022.9816178"},{"issue":"1","key":"8848_CR18","doi-asserted-by":"publisher","DOI":"10.1117\/1.AP.5.1.016004","volume":"5","author":"G Giamougiannis","year":"2023","unstructured":"Giamougiannis G, Tsakyridis A, Moralis-Pegios M, Mourgias-Alexandris G, Totovic AR, Dabos G, Kirtas M, Passalis N, Tefas A, Kalavrouziotis D, Syrivelis D, Bakopoulos P, Mentovich E, Lazovsky D, Pleros N (2023) Neuromorphic silicon photonics with 50 GHz tiled matrix multiplication for deep-learning applications. Adv Photonics 5(1):016004. https:\/\/doi.org\/10.1117\/1.AP.5.1.016004","journal-title":"Adv Photonics"},{"key":"8848_CR19","doi-asserted-by":"publisher","unstructured":"Passalis N, Kirtas M, Mourgias-Alexandris G, Dabos G, Pleros N, Tefas A (2021) Training noise-resilient recurrent photonic networks for financial time series analysis. In: 2020 28th european signal processing conference (EUSIPCO), pp 1556\u20131560 https:\/\/doi.org\/10.23919\/Eusipco47968.2020.9287649","DOI":"10.23919\/Eusipco47968.2020.9287649"},{"issue":"10","key":"8848_CR20","doi-asserted-by":"publisher","first-page":"3243","DOI":"10.1109\/JLT.2022.3171831","volume":"40","author":"M Moralis-Pegios","year":"2022","unstructured":"Moralis-Pegios M, Mourgias-Alexandris G, Tsakyridis A, Giamougiannis G, Totovic A, Dabos G, Passalis N, Kirtas M, Rutirawut T, Gardes FY, Tefas A, Pleros N (2022) Neuromorphic silicon photonics and hardware-aware deep learning for high-speed inference. J Lightwave Technol 40(10):3243\u20133254. https:\/\/doi.org\/10.1109\/JLT.2022.3171831","journal-title":"J Lightwave Technol"},{"key":"8848_CR21","doi-asserted-by":"publisher","unstructured":"Mourgias-Alexandris G, Tsakyridis A, Passalis N, Kirtas M, Tefas A, Rutirawut T, Gardes FY, Pleros N, Moralis-Pegios M (2021) 25gmac\/sec\/axon photonic neural networks with 7ghz bandwidth optics through channel response-aware training. In: 2021 European conference on optical communication (ECOC), pp. 1\u20134. https:\/\/doi.org\/10.1109\/ECOC52684.2021.9606097","DOI":"10.1109\/ECOC52684.2021.9606097"},{"issue":"7","key":"8848_CR22","doi-asserted-by":"publisher","first-page":"10664","DOI":"10.1364\/OE.452803","volume":"30","author":"G Mourgias-Alexandris","year":"2022","unstructured":"Mourgias-Alexandris G, Moralis-Pegios M, Tsakyridis A, Passalis N, Kirtas M, Tefas A, Rutirawut T, Gardes FY, Pleros N (2022) Channel response-aware photonic neural network accelerators for high-speed inference through bandwidth-limited optics. Opt Express 30(7):10664\u201310671. https:\/\/doi.org\/10.1364\/OE.452803","journal-title":"Opt Express"},{"issue":"1","key":"8848_CR23","doi-asserted-by":"publisher","first-page":"5572","DOI":"10.1038\/s41467-022-33259-z","volume":"13","author":"G Mourgias-Alexandris","year":"2022","unstructured":"Mourgias-Alexandris G, Moralis-Pegios M, Tsakyridis A, Simos S, Dabos G, Totovic A, Passalis N, Kirtas M, Rutirawut T, Gardes F et al (2022) Noise-resilient and high-speed deep learning with coherent silicon photonics. Nat Commun 13(1):5572","journal-title":"Nat Commun"},{"issue":"1","key":"8848_CR24","doi-asserted-by":"publisher","first-page":"140","DOI":"10.1109\/TETCI.2022.3182765","volume":"7","author":"M Kirtas","year":"2023","unstructured":"Kirtas M, Passalis N, Mourgias-Alexandris G, Dabos G, Pleros N, Tefas A (2023) Robust architecture-agnostic and noise resilient training of photonic deep learning models. IEEE Trans Emerging Top Comput Intell 7(1):140\u2013149. https:\/\/doi.org\/10.1109\/TETCI.2022.3182765","journal-title":"IEEE Trans Emerging Top Comput Intell"},{"key":"8848_CR25","doi-asserted-by":"publisher","unstructured":"Kirtas M, Passalis N, Oikonomou A, Mourgias-Alexandris G, Moralis-Pegios M, Pleros N, Tefas A (2022) Normalized post-training quantization for photonic neural networks. In: 2022 IEEE symposium series on computational intelligence (SSCI), pp. 657\u2013663. https:\/\/doi.org\/10.1109\/SSCI51031.2022.10022168","DOI":"10.1109\/SSCI51031.2022.10022168"},{"key":"8848_CR26","doi-asserted-by":"publisher","first-page":"427","DOI":"10.1007\/978-3-031-08223-8_35","volume-title":"Engineering applications of neural networks","author":"A Oikonomou","year":"2022","unstructured":"Oikonomou A, Kirtas M, Passalis N, Mourgias-Alexandris G, Moralis-Pegios M, Pleros N, Tefas A (2022) A robust, quantization-aware training method for photonic neural networks. In: Iliadis L, Jayne C, Tefas A, Pimenidis E (eds) Engineering applications of neural networks. Springer, Cham, pp 427\u2013438"},{"issue":"18","key":"8848_CR27","doi-asserted-by":"publisher","first-page":"15589","DOI":"10.1007\/s00521-022-07243-z","volume":"34","author":"E Paolini","year":"2022","unstructured":"Paolini E, De Marinis L, Cococcioni M, Valcarenghi L, Maggiani L, Andriolli N (2022) Photonic-aware neural networks. Neural Comput Appl 34(18):15589\u201315601","journal-title":"Neural Comput Appl"},{"key":"8848_CR28","doi-asserted-by":"publisher","first-page":"561","DOI":"10.1016\/j.neunet.2022.09.015","volume":"155","author":"M Kirtas","year":"2022","unstructured":"Kirtas M, Oikonomou A, Passalis N, Mourgias-Alexandris G, Moralis-Pegios M, Pleros N, Tefas A (2022) Quantization-aware training for low precision photonic neural networks. Neural Netw 155:561\u2013573. https:\/\/doi.org\/10.1016\/j.neunet.2022.09.015","journal-title":"Neural Netw"},{"key":"8848_CR29","unstructured":"Pearson C (2011) High-speed, analog-to-digital converter basics. Texas instruments application report, SLAA510"},{"key":"8848_CR30","doi-asserted-by":"publisher","unstructured":"Jacob B, Kligys S, Chen B, Zhu M, Tang M, Howard A, Adam H, Kalenichenko D (2018) Quantization and training of neural networks for efficient integer-arithmetic-only inference. Proc. IEEE computer society conf. on computer vision and pattern recognition, pp 2704\u20132713 https:\/\/doi.org\/10.1109\/CVPR.2018.00286arXiv:1712.05877","DOI":"10.1109\/CVPR.2018.00286"},{"key":"8848_CR31","doi-asserted-by":"publisher","first-page":"28","DOI":"10.1016\/j.neunet.2020.12.022","volume":"136","author":"U Kulkarni","year":"2021","unstructured":"Kulkarni U, Meena S, Gurlahosur SV, Bhogar G (2021) Quantization friendly mobilenet (qf-mobilenet) architecture for vision based applications on embedded platforms. Neural Netw 136:28\u201339","journal-title":"Neural Netw"},{"key":"8848_CR32","doi-asserted-by":"publisher","first-page":"420","DOI":"10.1016\/j.neunet.2021.05.034","volume":"141","author":"D Lee","year":"2021","unstructured":"Lee D, Wang D, Yang Y, Deng L, Zhao G, Li G (2021) Qttnet: quantized tensor train neural networks for 3d object and video recognition. Neural Netw 141:420\u2013432. https:\/\/doi.org\/10.1016\/j.neunet.2021.05.034","journal-title":"Neural Netw"},{"key":"8848_CR33","doi-asserted-by":"crossref","unstructured":"Wu J, Leng C, Wang Y, Hu Q, Cheng J (2016) Quantized convolutional neural networks for mobile devices. In: Proc. of the IEEE conf. on computer vision and pattern recognition, pp 4820\u20134828","DOI":"10.1109\/CVPR.2016.521"},{"key":"8848_CR34","unstructured":"Esser SK, McKinstry JL, Bablani D, Appuswamy R, Modha DS (2020) Learned step size quantization"},{"issue":"1","key":"8848_CR35","first-page":"6869","volume":"18","author":"I Hubara","year":"2017","unstructured":"Hubara I, Courbariaux M, Soudry D, El-Yaniv R, Bengio Y (2017) Quantized neural networks: training neural networks with low precision weights and activations. J Mac Learn Res 18(1):6869\u20136898","journal-title":"J Mac Learn Res"},{"issue":"7","key":"8848_CR36","doi-asserted-by":"publisher","first-page":"10664","DOI":"10.1364\/OE.452803","volume":"30","author":"G Mourgias-Alexandris","year":"2022","unstructured":"Mourgias-Alexandris G, Moralis-Pegios M, Tsakyridis A, Passalis N, Kirtas M, Tefas A, Rutirawut T, Gardes F, Pleros N (2022) Channel response-aware photonic neural network accelerators for high-speed inference through bandwidth-limited optics. Opt Express 30(7):10664\u201310671","journal-title":"Opt Express"},{"issue":"2","key":"8848_CR37","doi-asserted-by":"publisher","first-page":"102","DOI":"10.1038\/s41566-020-00754-y","volume":"15","author":"BJ Shastri","year":"2021","unstructured":"Shastri BJ, Tait AN, de Lima TF, Pernice WH, Bhaskaran H, Wright CD, Prucnal PR (2021) Photonics for artificial intelligence and neuromorphic computing. Nat Photonics 15(2):102\u2013114","journal-title":"Nat Photonics"},{"issue":"1","key":"8848_CR38","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/JSTQE.2019.2941485","volume":"26","author":"MA Nahmias","year":"2020","unstructured":"Nahmias MA, de Lima TF, Tait AN, Peng H-T, Shastri BJ, Prucnal PR (2020) Photonic multiply-accumulate operations for neural networks. IEEE J Sel Top Quantum Electron 26(1):1\u201318. https:\/\/doi.org\/10.1109\/JSTQE.2019.2941485","journal-title":"IEEE J Sel Top Quantum Electron"},{"key":"8848_CR39","doi-asserted-by":"publisher","unstructured":"Park E, Ahn J, Yoo S (2017) Weighted-entropy-based quantization for deep neural networks. In: 2017 IEEE conference on computer vision and pattern recognition (CVPR), pp 7197\u20137205. https:\/\/doi.org\/10.1109\/CVPR.2017.761","DOI":"10.1109\/CVPR.2017.761"},{"key":"8848_CR40","doi-asserted-by":"publisher","unstructured":"Courbariaux M, Bengio Y, David J-P (2014) Training deep neural networks with low precision multiplications. https:\/\/doi.org\/10.48550\/ARXIV.1412.7024. arXiv:org\/abs\/1412.7024","DOI":"10.48550\/ARXIV.1412.7024"},{"key":"8848_CR41","doi-asserted-by":"publisher","unstructured":"Gholami A, Kim S, Dong Z, Yao Z, Mahoney MW, Keutzer K (2021) A survey of quantization methods for efficient neural network inference. https:\/\/doi.org\/10.48550\/ARXIV.2103.13630. arXiv:org\/abs\/2103.13630","DOI":"10.48550\/ARXIV.2103.13630"},{"issue":"1","key":"8848_CR42","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1109\/TVLSI.2020.3020286","volume":"29","author":"B Murmann","year":"2021","unstructured":"Murmann B (2021) Mixed-signal computing for deep neural network inference. IEEE Trans Very Large Scale Integr VLSI Syst 29(1):3\u201313. https:\/\/doi.org\/10.1109\/TVLSI.2020.3020286","journal-title":"IEEE Trans Very Large Scale Integr VLSI Syst"},{"issue":"7","key":"8848_CR43","doi-asserted-by":"publisher","first-page":"1601","DOI":"10.1162\/089976698300017052","volume":"10","author":"R Sarpeshkar","year":"1998","unstructured":"Sarpeshkar R (1998) Analog versus digital: extrapolating from electronics to neurobiology. Neural Comput 10(7):1601\u20131638","journal-title":"Neural Comput"},{"key":"8848_CR44","doi-asserted-by":"publisher","unstructured":"Giamougiannis G, Tsakyridis A, Moralis-Pegios M, Totovic AR, Kirtas M, Passalis N, Tefas A, Lazovsky D, Pleros N (2023) Universal linear optics revisited: new perspectives for neuromorphic computing with silicon photonics. IEEE Journal of Selected Topics in Quantum Electronics 29(2: Optical Computing), 1\u201316 https:\/\/doi.org\/10.1109\/JSTQE.2022.3228318","DOI":"10.1109\/JSTQE.2022.3228318"},{"key":"8848_CR45","doi-asserted-by":"publisher","unstructured":"Giamougiannis G, Tsakyridis A, Moralis-Pegios M, Pappas C, Kirtas M, Passalis N, Lazovsky D, Tefas A, Pleros N (2023) Analog nanophotonic computing going practical: silicon photonic deep learning engines for tiled optical matrix multiplication with dynamic precision. Nanophotonics. https:\/\/doi.org\/10.1515\/nanoph-2022-0423","DOI":"10.1515\/nanoph-2022-0423"},{"key":"8848_CR46","unstructured":"Giamougiannis G, Tsakyridis A, Moralis-Pegios M, Pappas C, Kirtas M, Passalis N, Lazovsky D, Tefas A, Pleros N (2022) High-speed analog photonic computing with tiled matrix multiplication and dynamic precision capabilities for dnns. In: 2022 European Conference on Optical Communication (ECOC), pp. 1\u20134"},{"key":"8848_CR47","doi-asserted-by":"publisher","unstructured":"Mourgias-Alexandris G, Dabos G, Passalis N, Tefas A, Totovic A, Pleros N (2020) All-optical recurrent neural network with sigmoid activation function. In: Optical fiber communication conference (OFC) 2020, pp 3\u20135. Optica Publishing Group, https:\/\/doi.org\/10.1364\/OFC.2020.W3A.5. https:\/\/opg.optica.org\/abstract.cfm?URI=OFC-2020-W3A.5","DOI":"10.1364\/OFC.2020.W3A.5"},{"issue":"5","key":"8848_CR48","doi-asserted-by":"publisher","first-page":"1340","DOI":"10.1109\/JLT.2020.3038890","volume":"39","author":"G Mourgias-Alexandris","year":"2021","unstructured":"Mourgias-Alexandris G, Passalis N, Dabos G, Totovi\u0107 A, Tefas A, Pleros N (2021) A photonic recurrent neuron for time-series classification. J Lightwave Technol 39(5):1340\u20131347","journal-title":"J Lightwave Technol"},{"issue":"25","key":"8848_CR49","doi-asserted-by":"publisher","first-page":"22767","DOI":"10.1364\/OE.17.022767","volume":"17","author":"D Rosenbluth","year":"2009","unstructured":"Rosenbluth D, Kravtsov K, Fok MP, Prucnal PR (2009) A high performance photonic pulse processing device. Opt Express 17(25):22767\u201322772","journal-title":"Opt Express"},{"issue":"7","key":"8848_CR50","doi-asserted-by":"publisher","first-page":"9620","DOI":"10.1364\/OE.27.009620","volume":"27","author":"G Mourgias-Alexandris","year":"2019","unstructured":"Mourgias-Alexandris G, Tsakyridis A, Passalis N, Tefas A, Vyrsokinos K, Pleros N (2019) An all-optical neuron with sigmoid activation function. Opt Express 27(7):9620\u20139630","journal-title":"Opt Express"},{"key":"8848_CR51","doi-asserted-by":"crossref","unstructured":"Pitris S, Mitsolidou C, Alexoudi T, P\u00e9rez-Galacho D, Vivien L, Baudot C, De\u00a0Heyn P, Van\u00a0Campenhout J, Marris-Morini D, Pleros N (2018) O-band energy-efficient broadcast-friendly interconnection scheme with sipho mach-zehnder modulator (mzm) and arrayed waveguide grating router (awgr). In: 2018 optical fiber communications conference and exposition (OFC), pp 1\u20133","DOI":"10.1364\/OFC.2018.Th1G.5"},{"issue":"5","key":"8848_CR52","doi-asserted-by":"publisher","first-page":"396","DOI":"10.1109\/TETCI.2018.2849109","volume":"2","author":"L Danial","year":"2018","unstructured":"Danial L, Wainstein N, Kraus S, Kvatinsky S (2018) Breaking through the speed-power-accuracy tradeoff in ADCs using a memristive neuromorphic architecture. IEEE Trans Emerg Topics Comput Intell 2(5):396\u2013409. https:\/\/doi.org\/10.1109\/TETCI.2018.2849109","journal-title":"IEEE Trans Emerg Topics Comput Intell"},{"key":"8848_CR53","doi-asserted-by":"publisher","unstructured":"Garg S, Lou J, Jain A, Nahmias M (2021) Dynamic precision analog computing for neural networks. https:\/\/doi.org\/10.48550\/ARXIV.2102.06365. arXiv:org\/abs\/2102.06365","DOI":"10.48550\/ARXIV.2102.06365"},{"key":"8848_CR54","doi-asserted-by":"publisher","unstructured":"Wang K, Liu Z, Lin Y, Lin J, Han S (2018) HAQ: Hardware-aware automated quantization with mixed precision. https:\/\/doi.org\/10.48550\/ARXIV.1811.08886. arXiv:org\/abs\/1811.08886","DOI":"10.48550\/ARXIV.1811.08886"},{"key":"8848_CR55","doi-asserted-by":"crossref","unstructured":"Tishby N, Zaslavsky N (2015) Deep learning and the information bottleneck principle. In: Proc. IEEE information theory workshop, pp 1\u20135","DOI":"10.1109\/ITW.2015.7133169"},{"issue":"6","key":"8848_CR56","doi-asserted-by":"publisher","first-page":"17","DOI":"10.1109\/2.294849","volume":"27","author":"M Srinivas","year":"1994","unstructured":"Srinivas M, Patnaik LM (1994) Genetic algorithms: a survey. Computer 27(6):17\u201326. https:\/\/doi.org\/10.1109\/2.294849","journal-title":"Computer"},{"key":"8848_CR57","doi-asserted-by":"publisher","unstructured":"Pascanu R, Mikolov T, Bengio Y (2012) On the difficulty of training recurrent neural networks. https:\/\/doi.org\/10.48550\/ARXIV.1211.5063. arXiv:org\/abs\/1211.5063","DOI":"10.48550\/ARXIV.1211.5063"},{"key":"8848_CR58","doi-asserted-by":"publisher","first-page":"64722","DOI":"10.1109\/ACCESS.2019.2916793","volume":"7","author":"P Nousi","year":"2019","unstructured":"Nousi P et al (2019) Machine learning for forecasting mid-price movements using limit order book data. IEEE Access 7:64722\u201364736","journal-title":"IEEE Access"},{"issue":"11","key":"8848_CR59","doi-asserted-by":"publisher","first-page":"2278","DOI":"10.1109\/5.726791","volume":"86","author":"Y Lecun","year":"1998","unstructured":"Lecun Y, Bottou L, Bengio Y, Haffner P (1998) Gradient-based learning applied to document recognition. Proc IEEE 86(11):2278\u20132324. https:\/\/doi.org\/10.1109\/5.726791","journal-title":"Proc IEEE"},{"issue":"6","key":"8848_CR60","doi-asserted-by":"publisher","first-page":"84","DOI":"10.1145\/3065386","volume":"60","author":"A Krizhevsky","year":"2017","unstructured":"Krizhevsky A, Sutskever I, Hinton GE (2017) Imagenet classification with deep convolutional neural networks. Commun ACM 60(6):84\u201390. https:\/\/doi.org\/10.1145\/3065386","journal-title":"Commun ACM"},{"key":"8848_CR61","doi-asserted-by":"publisher","unstructured":"He K, Zhang X, Ren S, Sun J (2015) Deep residual learning for image recognition. https:\/\/doi.org\/10.48550\/ARXIV.1512.03385. arXiv:org\/abs\/1512.03385","DOI":"10.48550\/ARXIV.1512.03385"},{"key":"8848_CR62","unstructured":"Loshchilov I, Hutter F (2019) Decoupled weight decay regularization. In: International conference on learning representations. https:\/\/openreview.net\/forum?id=Bkg6RiCqY7"},{"key":"8848_CR63","unstructured":"M\u00fcller R, Kornblith S, Hinton GE (2019) When does label smoothing help? In: Advances in neural information processing systems 32 (NeurIPS 2019). https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2019\/hash\/f1748d6b0fd9d439f71450117eba2725-Abstract.html"},{"issue":"8","key":"8848_CR64","doi-asserted-by":"publisher","first-page":"852","DOI":"10.1002\/for.2543","volume":"37","author":"A Ntakaris","year":"2018","unstructured":"Ntakaris A, Magris M, Kanniainen J, Gabbouj M, Iosifidis A (2018) Benchmark dataset for mid-price forecasting of limit order book data with machine learning methods. J Forecast 37(8):852\u2013866","journal-title":"J Forecast"}],"container-title":["Neural Computing and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00521-023-08848-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00521-023-08848-8\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00521-023-08848-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,9,16]],"date-time":"2023-09-16T14:06:59Z","timestamp":1694873219000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00521-023-08848-8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,8,5]]},"references-count":64,"journal-issue":{"issue":"29","published-print":{"date-parts":[[2023,10]]}},"alternative-id":["8848"],"URL":"https:\/\/doi.org\/10.1007\/s00521-023-08848-8","relation":{},"ISSN":["0941-0643","1433-3058"],"issn-type":[{"value":"0941-0643","type":"print"},{"value":"1433-3058","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,8,5]]},"assertion":[{"value":"25 February 2023","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"28 June 2023","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"5 August 2023","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}