{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,19]],"date-time":"2026-06-19T15:50:11Z","timestamp":1781884211539,"version":"3.54.5"},"reference-count":65,"publisher":"Springer Science and Business Media LLC","issue":"18","license":[{"start":{"date-parts":[[2022,4,25]],"date-time":"2022-04-25T00:00:00Z","timestamp":1650844800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2022,4,25]],"date-time":"2022-04-25T00:00:00Z","timestamp":1650844800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Neural Comput &amp; Applic"],"published-print":{"date-parts":[[2022,9]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:p>Photonics-based neural networks promise to outperform electronic counterparts, accelerating neural network computations while reducing power consumption and footprint. However, these solutions suffer from physical layer constraints arising from the underlying analog photonic hardware, impacting the resolution of computations (in terms of effective number of bits), requiring the use of positive-valued inputs, and imposing limitations in the fan-in and in the size of convolutional kernels. To abstract these constraints, in this paper we introduce the concept of Photonic-Aware Neural Network (PANN) architectures, i.e., deep neural network models aware of the photonic hardware constraints. Then, we devise PANN training schemes resorting to quantization strategies aimed to obtain the required neural network parameters in the fixed-point domain, compliant with the limited resolution of the underlying hardware. We finally carry out extensive simulations exploiting PANNs in image classification tasks on well-known datasets (MNIST, Fashion-MNIST, and Cifar-10) with varying bitwidths (i.e., 2, 4, and 6 bits). We consider two kernel sizes and two pooling schemes for each PANN model, exploiting <jats:inline-formula><jats:alternatives><jats:tex-math>$$2\\times 2$$<\/jats:tex-math><mml:math xmlns:mml=\"http:\/\/www.w3.org\/1998\/Math\/MathML\">\n                  <mml:mrow>\n                    <mml:mn>2<\/mml:mn>\n                    <mml:mo>\u00d7<\/mml:mo>\n                    <mml:mn>2<\/mml:mn>\n                  <\/mml:mrow>\n                <\/mml:math><\/jats:alternatives><\/jats:inline-formula> and <jats:inline-formula><jats:alternatives><jats:tex-math>$$3\\times 3$$<\/jats:tex-math><mml:math xmlns:mml=\"http:\/\/www.w3.org\/1998\/Math\/MathML\">\n                  <mml:mrow>\n                    <mml:mn>3<\/mml:mn>\n                    <mml:mo>\u00d7<\/mml:mo>\n                    <mml:mn>3<\/mml:mn>\n                  <\/mml:mrow>\n                <\/mml:math><\/jats:alternatives><\/jats:inline-formula> convolutional kernels, and max and average pooling, the latter more amenable to an optical implementation. <jats:inline-formula><jats:alternatives><jats:tex-math>$$3\\times 3$$<\/jats:tex-math><mml:math xmlns:mml=\"http:\/\/www.w3.org\/1998\/Math\/MathML\">\n                  <mml:mrow>\n                    <mml:mn>3<\/mml:mn>\n                    <mml:mo>\u00d7<\/mml:mo>\n                    <mml:mn>3<\/mml:mn>\n                  <\/mml:mrow>\n                <\/mml:math><\/jats:alternatives><\/jats:inline-formula> kernels perform better than <jats:inline-formula><jats:alternatives><jats:tex-math>$$2\\times 2$$<\/jats:tex-math><mml:math xmlns:mml=\"http:\/\/www.w3.org\/1998\/Math\/MathML\">\n                  <mml:mrow>\n                    <mml:mn>2<\/mml:mn>\n                    <mml:mo>\u00d7<\/mml:mo>\n                    <mml:mn>2<\/mml:mn>\n                  <\/mml:mrow>\n                <\/mml:math><\/jats:alternatives><\/jats:inline-formula> counterparts, while max and average pooling provide comparable results, with the latter performing better on MNIST and Cifar-10. The accuracy degradation due to the photonic hardware constraints is quite limited, especially on MNIST and Fashion-MNIST, demonstrating the feasibility of PANN approaches on computer vision tasks.<\/jats:p>","DOI":"10.1007\/s00521-022-07243-z","type":"journal-article","created":{"date-parts":[[2022,4,25]],"date-time":"2022-04-25T07:06:53Z","timestamp":1650870413000},"page":"15589-15601","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":34,"title":["Photonic-aware neural networks"],"prefix":"10.1007","volume":"34","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7486-9268","authenticated-orcid":false,"given":"Emilio","family":"Paolini","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lorenzo","family":"De Marinis","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Marco","family":"Cococcioni","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Luca","family":"Valcarenghi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Luca","family":"Maggiani","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Nicola","family":"Andriolli","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2022,4,25]]},"reference":[{"key":"7243_CR1","unstructured":"Sinha R, Pandey R, Pattnaik R (2018) Deep learning for computer vision tasks: a review"},{"key":"7243_CR2","doi-asserted-by":"publisher","DOI":"10.1145\/3065386","author":"A Krizhevsky","year":"2012","unstructured":"Krizhevsky A, Sutskever I, Hinton G (2012) ImageNet classification with deep convolutional neural networks. Neural Inf Process Syst. https:\/\/doi.org\/10.1145\/3065386","journal-title":"Neural Inf Process Syst"},{"issue":"1","key":"7243_CR3","doi-asserted-by":"publisher","first-page":"30","DOI":"10.1109\/TASL.2011.2134090","volume":"20","author":"GE Dahl","year":"2012","unstructured":"Dahl GE, Yu D, Deng L, Acero A (2012) Context-dependent pre-trained deep neural networks for large-vocabulary speech recognition. IEEE Trans Audio Speech Lang Process 20(1):30\u201342. https:\/\/doi.org\/10.1109\/TASL.2011.2134090","journal-title":"IEEE Trans Audio Speech Lang Process"},{"key":"7243_CR4","doi-asserted-by":"publisher","unstructured":"Soundarya B, Krishnaraj R, Mythili MS (2021) Visual speech recognition using convolutional neural network. In: IOP conference series: materials science and engineering, vol 1084, p 012020. https:\/\/doi.org\/10.1088\/1757-899X\/1084\/1\/012020","DOI":"10.1088\/1757-899X\/1084\/1\/012020"},{"key":"7243_CR5","doi-asserted-by":"publisher","unstructured":"Zhang Z, Huang S (2020) Credit card fraud detection via deep learning method using data balance tools. In: 2020 international conference on computer science and management technology (ICCSMT), pp 133\u2013137. https:\/\/doi.org\/10.1109\/ICCSMT51754.2020.00033","DOI":"10.1109\/ICCSMT51754.2020.00033"},{"key":"7243_CR6","doi-asserted-by":"publisher","first-page":"100379","DOI":"10.1016\/j.cosrev.2021.100379","volume":"40","author":"S Dong","year":"2021","unstructured":"Dong S, Wang P, Abbas K (2021) A survey on deep learning and its applications. Comput Sci Rev 40:100379","journal-title":"Comput Sci Rev"},{"issue":"4","key":"7243_CR7","doi-asserted-by":"publisher","first-page":"27","DOI":"10.1109\/85.238389","volume":"15","author":"J Von Neumann","year":"1993","unstructured":"Von Neumann J (1993) First draft of a report on the EDVAC. IEEE Ann Hist Comput 15(4):27\u201375","journal-title":"IEEE Ann Hist Comput"},{"issue":"1","key":"7243_CR8","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3289185","volume":"12","author":"K Guo","year":"2019","unstructured":"Guo K, Zeng S, Yu J, Wang Y, Yang H (2019) [DL] A survey of FPGA-based neural network inference accelerators. ACM Trans Reconfig Technol Syst 12(1):1\u201326. https:\/\/doi.org\/10.1145\/3289185","journal-title":"ACM Trans Reconfig Technol Syst"},{"issue":"6","key":"7243_CR9","doi-asserted-by":"publisher","first-page":"1138","DOI":"10.1109\/TBCAS.2020.3036081","volume":"14","author":"MR Azghadi","year":"2020","unstructured":"Azghadi MR, Lammie C, Eshraghian JK, Payvand M, Donati E, Linares-Barranco B, Indiveri G (2020) Hardware implementation of deep network accelerators towards healthcare and biomedical applications. IEEE Trans Biomed Circuits Syst 14(6):1138\u20131159. https:\/\/doi.org\/10.1109\/TBCAS.2020.3036081","journal-title":"IEEE Trans Biomed Circuits Syst"},{"issue":"2","key":"7243_CR10","doi-asserted-by":"publisher","first-page":"7","DOI":"10.1109\/MCSE.2017.31","volume":"19","author":"RS Williams","year":"2017","unstructured":"Williams RS (2017) What\u2019s next? [the end of Moore\u2019s law]. Comput Sci Eng 19(2):7\u201313. https:\/\/doi.org\/10.1109\/MCSE.2017.31","journal-title":"Comput Sci Eng"},{"key":"7243_CR11","doi-asserted-by":"publisher","unstructured":"Hamerly R, Sludds A, Bernstein L, Prabhu M, Roques-Carmes C, Carolan J, Yamamoto Y, Solja\u010di\u0107 M, Englund D (2019) Towards large-scale photonic neural-network accelerators. In: 2019 IEEE international electron devices meeting (IEDM), pp 22.8.1\u201322.8.4. https:\/\/doi.org\/10.1109\/IEDM19573.2019.8993624","DOI":"10.1109\/IEDM19573.2019.8993624"},{"key":"7243_CR12","unstructured":"Schuman CD, Potok TE, Patton RM, Birdwell JD, Dean ME, Rose GS, Plank JS (2017) A survey of neuromorphic computing and neural networks in hardware. arXiv preprint arXiv:1705.06963"},{"issue":"8","key":"7243_CR13","doi-asserted-by":"publisher","first-page":"1245","DOI":"10.1109\/JPROC.2019.2897076","volume":"108","author":"D Shin","year":"2020","unstructured":"Shin D, Yoo H-J (2020) The heterogeneous deep neural network processor with a non-von Neumann architecture. Proc IEEE 108(8):1245\u20131260. https:\/\/doi.org\/10.1109\/JPROC.2019.2897076","journal-title":"Proc IEEE"},{"issue":"1","key":"7243_CR14","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":"7243_CR15","doi-asserted-by":"publisher","first-page":"175827","DOI":"10.1109\/ACCESS.2019.2957245","volume":"7","author":"L De Marinis","year":"2019","unstructured":"De Marinis L, Cococcioni M, Castoldi P, Andriolli N (2019) Photonic neural networks: a survey. IEEE Access 7:175827\u2013175841. https:\/\/doi.org\/10.1109\/ACCESS.2019.2957245","journal-title":"IEEE Access"},{"key":"7243_CR16","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/JSTQE.2019.2945540","volume":"26","author":"V Bangari","year":"2020","unstructured":"Bangari V, Marquez BA, Miller HB, Tait AN, Nahmias MA, de Lima TF, Peng H-T, Prucnal PR, Shastri BJ (2020) Digital electronics and analog photonics for convolutional neural networks (DEAP-CNNs). IEEE J Sel Top Quantum Electron 26:1\u201313","journal-title":"IEEE J Sel Top Quantum Electron"},{"issue":"12","key":"7243_CR17","doi-asserted-by":"publisher","first-page":"3851","DOI":"10.1364\/OME.8.003851","volume":"8","author":"M Miscuglio","year":"2018","unstructured":"Miscuglio M, Mehrabian A, Hu Z, Azzam SI, George J, Kildishev AV, Pelton M, Sorger VJ (2018) All-optical nonlinear activation function for photonic neural networks. Opt Mater Express 8(12):3851\u20133863. https:\/\/doi.org\/10.1364\/OME.8.003851","journal-title":"Opt Mater Express"},{"issue":"7","key":"7243_CR18","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"},{"issue":"4","key":"7243_CR19","doi-asserted-by":"publisher","first-page":"5181","DOI":"10.1364\/OE.27.005181","volume":"27","author":"JK George","year":"2019","unstructured":"George JK, Mehrabian A, Amin R, Meng J, De Lima TF, Tait AN, Shastri BJ, El-Ghazawi T, Prucnal PR, Sorger VJ (2019) Neuromorphic photonics with electro-absorption modulators. Opt Express 27(4):5181\u20135191","journal-title":"Opt Express"},{"issue":"1","key":"7243_CR20","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/JSTQE.2019.2930455","volume":"26","author":"IAD Williamson","year":"2020","unstructured":"Williamson IAD, Hughes TW, Minkov M, Bartlett B, Pai S, Fan S (2020) Reprogrammable electro-optic nonlinear activation functions for optical neural networks. IEEE J Sel Top Quantum Electron 26(1):1\u201312. https:\/\/doi.org\/10.1109\/JSTQE.2019.2930455","journal-title":"IEEE J Sel Top Quantum Electron"},{"key":"7243_CR21","unstructured":"Bartlett B, Minkov M, Hughes T, Williamson IAD (2019) Neuroptica: flexible simulation package for optical neural networks. GitHub https:\/\/github.com\/fancompute\/neuroptica"},{"key":"7243_CR22","doi-asserted-by":"crossref","unstructured":"Pai S, Williamson IA, Hughes TW, Minkov M, Solgaard O, Fan S, Miller DA (2019) Parallel fault-tolerant programming of an arbitrary feedforward photonic network. arXiv preprint arXiv:1909.06179","DOI":"10.1364\/CLEO_SI.2020.SM1E.5"},{"issue":"6","key":"7243_CR23","doi-asserted-by":"publisher","first-page":"064044","DOI":"10.1103\/PhysRevApplied.11.064044","volume":"11","author":"S Pai","year":"2019","unstructured":"Pai S, Bartlett B, Solgaard O, Miller DAB (2019) Matrix optimization on universal unitary photonic devices. Phys Rev Appl 11(6):064044. https:\/\/doi.org\/10.1103\/PhysRevApplied.11.064044","journal-title":"Phys Rev Appl"},{"issue":"45","key":"7243_CR24","doi-asserted-by":"publisher","first-page":"1746","DOI":"10.21105\/joss.01746","volume":"5","author":"L Geiger","year":"2020","unstructured":"Geiger L, Team P (2020) An open-source library for training binarized neural networks. J Open Source Softw 5(45):1746. https:\/\/doi.org\/10.21105\/joss.01746","journal-title":"J Open Source Softw"},{"issue":"7","key":"7243_CR25","doi-asserted-by":"publisher","first-page":"1337","DOI":"10.1109\/JPROC.2009.2020712","volume":"97","author":"AV Krishnamoorthy","year":"2009","unstructured":"Krishnamoorthy AV, Ho R, Zheng X, Schwetman H, Lexau J, Koka P, Li G, Shubin I, Cunningham JE (2009) Computer systems based on silicon photonic interconnects. Proc IEEE 97(7):1337\u20131361","journal-title":"Proc IEEE"},{"issue":"7836","key":"7243_CR26","doi-asserted-by":"publisher","first-page":"39","DOI":"10.1038\/s41586-020-2973-6","volume":"588","author":"G Wetzstein","year":"2020","unstructured":"Wetzstein G, Ozcan A, Gigan S, Fan S, Englund D, Solja\u010di\u0107 M, Denz C, Miller DA, Psaltis D (2020) Inference in artificial intelligence with deep optics and photonics. Nature 588(7836):39\u201347","journal-title":"Nature"},{"issue":"6","key":"7243_CR27","doi-asserted-by":"publisher","first-page":"1428","DOI":"10.1109\/2944.902198","volume":"6","author":"KE Stubkjaer","year":"2000","unstructured":"Stubkjaer KE (2000) Semiconductor optical amplifier-based all-optical gates for high-speed optical processing. IEEE J Sel Top Quantum Electron 6(6):1428\u20131435. https:\/\/doi.org\/10.1109\/2944.902198","journal-title":"IEEE J Sel Top Quantum Electron"},{"issue":"10","key":"7243_CR28","doi-asserted-by":"publisher","first-page":"1436","DOI":"10.1109\/LPT.2002.801841","volume":"14","author":"JH Kim","year":"2002","unstructured":"Kim JH, Jhon YM, Byun YT, Lee S, Woo DH, Kim SH (2002) All-optical XOR gate using semiconductor optical amplifiers without additional input beam. IEEE Photon Technol Lett 14(10):1436\u20131438. https:\/\/doi.org\/10.1109\/LPT.2002.801841","journal-title":"IEEE Photon Technol Lett"},{"issue":"23","key":"7243_CR29","doi-asserted-by":"publisher","first-page":"3955","DOI":"10.1364\/OL.35.003955","volume":"35","author":"A Bogoni","year":"2010","unstructured":"Bogoni A, Wu X, Bakhtiari Z, Nuccio S, Willner AE (2010) 640 Gbits\/s photonic logic gates. Opt Lett 35(23):3955\u20133957","journal-title":"Opt Lett"},{"issue":"7553","key":"7243_CR30","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"},{"issue":"6","key":"7243_CR31","doi-asserted-by":"publisher","first-page":"8:1","DOI":"10.1147\/JRD.2019.2934050","volume":"63","author":"H-Y Chang","year":"2019","unstructured":"Chang H-Y, Narayanan P, Lewis SC, Farinha NC, Hosokawa K, Mackin C, Tsai H, Ambrogio S, Chen A, Burr GW (2019) AI hardware acceleration with analog memory: microarchitectures for low energy at high speed. IBM J Res Dev 63(6):8:1-8:14","journal-title":"IBM J Res Dev"},{"issue":"1","key":"7243_CR32","doi-asserted-by":"publisher","first-page":"108","DOI":"10.1109\/JPROC.2018.2871057","volume":"107","author":"W Haensch","year":"2018","unstructured":"Haensch W, Gokmen T, Puri R (2018) The next generation of deep learning hardware: analog computing. Proc IEEE 107(1):108\u2013122","journal-title":"Proc IEEE"},{"key":"7243_CR33","doi-asserted-by":"publisher","first-page":"203525","DOI":"10.1109\/ACCESS.2020.3037017","volume":"8","author":"M Paliy","year":"2020","unstructured":"Paliy M, Strangio S, Ruiu P, Rizzo T, Iannaccone G (2020) Analog vector-matrix multiplier based on programmable current mirrors for neural network integrated circuits. IEEE Access 8:203525\u2013203537","journal-title":"IEEE Access"},{"key":"7243_CR34","first-page":"19","volume":"8","author":"D Brunner","year":"2019","unstructured":"Brunner D, Soriano MC, Van der Sande G (2019) Photonic reservoir computing. De Gruyter 8:19","journal-title":"De Gruyter"},{"issue":"2","key":"7243_CR35","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 Photon 15(2):102\u2013114","journal-title":"Nat Photon"},{"issue":"7840","key":"7243_CR36","doi-asserted-by":"publisher","first-page":"44","DOI":"10.1038\/s41586-020-03063-0","volume":"589","author":"X Xu","year":"2021","unstructured":"Xu X, Tan M, Corcoran B, Wu J, Boes A, Nguyen TG, Chu ST, Little BE, Hicks DG, Morandotti R et al (2021) 11 TOPS photonic convolutional accelerator for optical neural networks. Nature 589(7840):44\u201351","journal-title":"Nature"},{"issue":"5","key":"7243_CR37","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","journal-title":"IEEE J Sel Top Quantum Electron"},{"issue":"7","key":"7243_CR38","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 Photon 11(7):441\u2013446","journal-title":"Nat Photon"},{"issue":"4","key":"7243_CR39","doi-asserted-by":"publisher","first-page":"811","DOI":"10.1109\/JLT.2019.2949133","volume":"38","author":"G Mourgias-Alexandris","year":"2019","unstructured":"Mourgias-Alexandris G, Totovi\u0107 A, Tsakyridis A, Passalis N, Vyrsokinos K, Tefas A, Pleros N (2019) Neuromorphic photonics with coherent linear neurons using dual-IQ modulation cells. J Lightw Technol 38(4):811\u2013819","journal-title":"J Lightw Technol"},{"issue":"13","key":"7243_CR40","doi-asserted-by":"publisher","first-page":"6232","DOI":"10.3390\/app11136232","volume":"11","author":"L De Marinis","year":"2021","unstructured":"De Marinis L, Cococcioni M, Liboiron-Ladouceur O, Contestabile G, Castoldi P, Andriolli N (2021) Photonic integrated reconfigurable linear processors as neural network accelerators. Appl Sci 11(13):6232","journal-title":"Appl Sci"},{"key":"7243_CR41","doi-asserted-by":"crossref","unstructured":"Huang C, Fujisawa S, De\u00a0Lima TF, Tait AN, Blow E, Tian Y, Bilodeau S, Jha A, Yaman F, Batshon HG et al (2020) Demonstration of photonic neural network for fiber nonlinearity compensation in long-haul transmission systems. In: 2020 optical fiber communications conference and exhibition (OFC), pp 1\u20133. IEEE","DOI":"10.1364\/OFC.2020.Th4C.6"},{"issue":"1","key":"7243_CR42","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/JSTQE.2019.2945548","volume":"26","author":"B Shi","year":"2019","unstructured":"Shi B, Calabretta N, Stabile R (2019) Deep neural network through an InP SOA-based photonic integrated cross-connect. IEEE J Sel Top Quantum Electron 26(1):1\u201311","journal-title":"IEEE J Sel Top Quantum Electron"},{"key":"7243_CR43","doi-asserted-by":"crossref","unstructured":"De\u00a0Marinis L, Catania A, Castoldi P, Bruschi P, Piotto M, Andriolli N (2021) A codesigned photonic electronic MAC neuron with ADC-embedded nonlinearity. In: CLEO: science and innovations, pp 3\u20134. Optical Society of America","DOI":"10.1364\/CLEO_SI.2021.AW3E.4"},{"issue":"1","key":"7243_CR44","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/JSTQE.2019.2931252","volume":"26","author":"TF de Lima","year":"2020","unstructured":"de Lima TF, Tait AN, Saeidi H, Nahmias MA, Peng H-T, Abbaslou S, Shastri BJ, Prucnal PR (2020) Noise analysis of photonic modulator neurons. IEEE J Sel Top Quantum Electron 26(1):1\u20139. https:\/\/doi.org\/10.1109\/JSTQE.2019.2931252","journal-title":"IEEE J Sel Top Quantum Electron"},{"issue":"13","key":"7243_CR45","doi-asserted-by":"publisher","first-page":"4221","DOI":"10.1515\/nanoph-2020-0297","volume":"9","author":"P Stark","year":"2020","unstructured":"Stark P, Horst F, Dangel R, Weiss J, Offrein BJ (2020) Opportunities for integrated photonic neural networks. Nanophotonics 9(13):4221\u20134232","journal-title":"Nanophotonics"},{"key":"7243_CR46","unstructured":"Glorot X, Bordes A, Bengio Y (2011) Deep sparse rectifier neural networks. In: Gordon G, Dunson D, Dud\u00edk M (eds) Proceedings of the fourteenth international conference on artificial intelligence and statistics. Proceedings of machine learning research, vol 15. PMLR, Fort Lauderdale, FL, USA, pp 315\u2013323. https:\/\/proceedings.mlr.press\/v15\/glorot11a.html"},{"issue":"3","key":"7243_CR47","doi-asserted-by":"publisher","first-page":"759","DOI":"10.1007\/s11554-020-00984-x","volume":"17","author":"M Cococcioni","year":"2020","unstructured":"Cococcioni M, Rossi F, Ruffaldi E, Saponara S (2020) Fast deep neural networks for image processing using posits and ARM scalable vector extension. J Real-Time Image Process 17(3):759\u2013771. https:\/\/doi.org\/10.1007\/s11554-020-00984-x","journal-title":"J Real-Time Image Process"},{"key":"7243_CR48","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2022.3149787","author":"M Wang","year":"2022","unstructured":"Wang M, Rasoulinezhad S, Leong PHW, So HK-H (2022) NITI: training integer neural networks using integer-only arithmetic. IEEE Trans Parallel Distrib Syst. https:\/\/doi.org\/10.1109\/TPDS.2022.3149787","journal-title":"IEEE Trans Parallel Distrib Syst"},{"key":"7243_CR49","unstructured":"Shin S, Hwang K, Sung W (2016) Quantized neural network design under weight capacity constraint. arXiv preprint arXiv:1611.06342"},{"issue":"1","key":"7243_CR50","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 Mach Learn Res 18(1):6869\u20136898","journal-title":"J Mach Learn Res"},{"key":"7243_CR51","doi-asserted-by":"crossref","unstructured":"Rastegari M, Ordonez V, Redmon J, Farhadi A (2016) XNOR-Net: ImageNet classification using binary convolutional neural networks. CoRR arXiv:abs\/1603.05279","DOI":"10.1007\/978-3-319-46493-0_32"},{"key":"7243_CR52","unstructured":"Courbariaux M, Bengio Y (2016) BinaryNet: training deep neural networks with weights and activations constrained to +1 or $$-$$\u00a01. CoRR arXiv:abs\/1602.02830"},{"key":"7243_CR53","unstructured":"Zhou S, Ni Z, Zhou X, Wen H, Wu Y, Zou Y (2016) DoReFa-Net: training low bitwidth convolutional neural networks with low bitwidth gradients. CoRR arXiv:abs\/1606.06160"},{"key":"7243_CR54","first-page":"1","volume":"32","author":"K Helwegen","year":"2019","unstructured":"Helwegen K, Widdicombe J, Geiger L, Liu Z, Cheng K-T, Nusselder R (2019) Latent weights do not exist: rethinking binarized neural network optimization. Adv Neural Inf Process Syst 32:1\u201312","journal-title":"Adv Neural Inf Process Syst"},{"key":"7243_CR55","unstructured":"Bengio Y, L\u00e9onard N, Courville AC (2013) Estimating or propagating gradients through stochastic neurons for conditional computation. CoRR arXiv:abs\/1308.3432"},{"key":"7243_CR56","unstructured":"LeCun Y, Cortes C (2010) MNIST handwritten digit database"},{"key":"7243_CR57","unstructured":"Xiao H, Rasul K, Vollgraf R (2017) Fashion-MNIST: a novel image dataset for benchmarking machine learning algorithms. CoRR arXiv:abs\/1708.07747"},{"key":"7243_CR58","unstructured":"Krizhevsky A, Nair V, Hinton G. CIFAR-10 (Canadian Institute for Advanced Research)"},{"issue":"11","key":"7243_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","journal-title":"Proc IEEE"},{"key":"7243_CR60","unstructured":"Guo Y (2018) A survey on methods and theories of quantized neural networks. arXiv preprint arXiv:1808.04752"},{"key":"7243_CR61","unstructured":"Ioffe S, Szegedy C (2015) Batch normalization: accelerating deep network training by reducing internal covariate shift. CoRR arXiv:abs\/1502.03167"},{"key":"7243_CR62","doi-asserted-by":"crossref","unstructured":"De\u00a0Marinis L, Nesti F, Cococcioni M, Andriolli N (2020) A photonic accelerator for feature map generation in convolutional neural networks. In: Photonics in switching and computing. Optical Society of America, pp 1\u20133","DOI":"10.1364\/PSC.2020.PsTh1F.3"},{"key":"7243_CR63","unstructured":"Courbariaux M, Bengio Y, David J (2015) BinaryConnect: training deep neural networks with binary weights during propagations. CoRR arXiv:abs\/1511.00363"},{"key":"7243_CR64","unstructured":"Kingma DP, Ba J (2014) Adam: a method for stochastic optimization. arXiv preprint arXiv:1412.6980"},{"issue":"4","key":"7243_CR65","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3459009","volume":"17","author":"FP Sunny","year":"2021","unstructured":"Sunny FP, Taheri E, Nikdast M, Pasricha S (2021) A survey on silicon photonics for deep learning. J Emerg Technol Comput Syst 17(4):1\u201357. https:\/\/doi.org\/10.1145\/3459009","journal-title":"J Emerg Technol Comput Syst"}],"container-title":["Neural Computing and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00521-022-07243-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00521-022-07243-z\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00521-022-07243-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,9,1]],"date-time":"2022-09-01T18:21:54Z","timestamp":1662056514000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00521-022-07243-z"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,4,25]]},"references-count":65,"journal-issue":{"issue":"18","published-print":{"date-parts":[[2022,9]]}},"alternative-id":["7243"],"URL":"https:\/\/doi.org\/10.1007\/s00521-022-07243-z","relation":{},"ISSN":["0941-0643","1433-3058"],"issn-type":[{"value":"0941-0643","type":"print"},{"value":"1433-3058","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,4,25]]},"assertion":[{"value":"18 January 2022","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"29 March 2022","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"25 April 2022","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"29 July 2022","order":4,"name":"change_date","label":"Change Date","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"Update","order":5,"name":"change_type","label":"Change Type","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"Missing Open Access funding information has been added in the\nFunding Note","order":6,"name":"change_details","label":"Change Details","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"All authors certify that they have no affiliations with or involvement in any organization or entity with any financial interest or non-financial interest in the subject matter or materials discussed in this manuscript.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interests"}}]}}