{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,11]],"date-time":"2026-03-11T16:40:14Z","timestamp":1773247214582,"version":"3.50.1"},"reference-count":49,"publisher":"Springer Science and Business Media LLC","issue":"7","license":[{"start":{"date-parts":[[2023,2,24]],"date-time":"2023-02-24T00:00:00Z","timestamp":1677196800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,2,24]],"date-time":"2023-02-24T00:00:00Z","timestamp":1677196800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/100010661","name":"Horizon 2020 Framework Programme","doi-asserted-by":"publisher","award":["871391"],"award-info":[{"award-number":["871391"]}],"id":[{"id":"10.13039\/100010661","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Neural Process Lett"],"published-print":{"date-parts":[[2023,12]]},"DOI":"10.1007\/s11063-023-11170-y","type":"journal-article","created":{"date-parts":[[2023,2,24]],"date-time":"2023-02-24T14:02:57Z","timestamp":1677247377000},"page":"8589-8604","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["Mutual Information-Based Neural Network Distillation for Improving Photonic Neural Network Training"],"prefix":"10.1007","volume":"55","author":[{"given":"Alexandros","family":"Chariton","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1177-9139","authenticated-orcid":false,"given":"Nikolaos","family":"Passalis","sequence":"additional","affiliation":[]},{"given":"Nikos","family":"Pleros","sequence":"additional","affiliation":[]},{"given":"Anastasios","family":"Tefas","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2023,2,24]]},"reference":[{"key":"11170_CR1","doi-asserted-by":"crossref","unstructured":"Ahn S, Hu SX, Damianou A, et\u00a0al (2019) Variational information distillation for knowledge transfer. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 9163\u20139171","DOI":"10.1109\/CVPR.2019.00938"},{"key":"11170_CR2","doi-asserted-by":"crossref","unstructured":"Banerjee S, Nikdast M, Chakrabarty K (2021) Optimizing coherent integrated photonic neural networks under random uncertainties. In: 2021 optical fiber communications conference and exhibition (OFC), pp 1\u20133","DOI":"10.1364\/OFC.2021.Th1A.22"},{"key":"11170_CR3","doi-asserted-by":"crossref","unstructured":"Chen D, Mei JP, Wang C, et\u00a0al (2020) Online knowledge distillation with diverse peers. In: Proceedings of the AAAI conference on artificial intelligence, pp 3430\u20133437","DOI":"10.1609\/aaai.v34i04.5746"},{"key":"11170_CR4","unstructured":"Chetlur S, Woolley C, Vandermersch P, et\u00a0al (2014) cudnn: Efficient primitives for deep learning. arXiv:1410.0759"},{"key":"11170_CR5","doi-asserted-by":"publisher","first-page":"175,827","DOI":"10.1109\/ACCESS.2019.2957245","volume":"7","author":"L De Marinis","year":"2019","unstructured":"De Marinis L, Cococcioni M, Castoldi P et al (2019) Photonic neural networks: a survey. IEEE Access 7:175,827-175,841","journal-title":"IEEE Access"},{"key":"11170_CR6","unstructured":"Glorot X, Bordes A, Bengio Y (2011) Deep sparse rectifier neural networks. In: Proceedings of the conference on artificial intelligence and statistics, pp 315\u2013323"},{"issue":"6","key":"11170_CR7","doi-asserted-by":"publisher","first-page":"1789","DOI":"10.1007\/s11263-021-01453-z","volume":"129","author":"J Gou","year":"2021","unstructured":"Gou J, Yu B, Maybank SJ et al (2021) Knowledge distillation: a survey. Int J Comput Vis 129(6):1789\u20131819","journal-title":"Int J Comput Vis"},{"key":"11170_CR8","first-page":"8649","volume":"34","author":"J Gu","year":"2021","unstructured":"Gu J, Zhu H, Feng C et al (2021) L2ight: Enabling on-chip learning for optical neural networks via efficient in-situ subspace optimization. Adv Neural Inf Process Syst 34:8649\u20138661","journal-title":"Adv Neural Inf Process Syst"},{"key":"11170_CR9","doi-asserted-by":"crossref","unstructured":"He K, Zhang X, Ren S, et\u00a0al (2015) Delving deep into rectifiers: surpassing human-level performance on imagenet classification. In: Proceedings of the international conference on computer vision, pp 1026\u20131034","DOI":"10.1109\/ICCV.2015.123"},{"key":"11170_CR10","unstructured":"Hinton G, Vinyals O, Dean J, et\u00a0al (2015) Distilling the knowledge in a neural network. 2(7) arXiv:1503.02531"},{"key":"11170_CR11","unstructured":"Huang Z, Wang N (2017) Like what you like: knowledge distill via neuron selectivity transfer. arXiv:1707.01219"},{"issue":"7","key":"11170_CR12","doi-asserted-by":"publisher","first-page":"864","DOI":"10.1364\/OPTICA.5.000864","volume":"5","author":"TW Hughes","year":"2018","unstructured":"Hughes TW, Minkov M, Shi Y et al (2018) Training of photonic neural networks through in situ backpropagation and gradient measurement. Optica 5(7):864\u2013871","journal-title":"Optica"},{"key":"11170_CR13","doi-asserted-by":"publisher","first-page":"73","DOI":"10.3389\/fnins.2011.00073","volume":"5","author":"G Indiveri","year":"2011","unstructured":"Indiveri G, Linares-Barranco B, Hamilton TJ et al (2011) Neuromorphic silicon neuron circuits. Front Neurosci 5:73","journal-title":"Front Neurosci"},{"issue":"3","key":"11170_CR14","doi-asserted-by":"publisher","first-page":"316","DOI":"10.1007\/s11263-009-0285-2","volume":"87","author":"H J\u00e9gou","year":"2010","unstructured":"J\u00e9gou H, Douze M, Schmid C (2010) Improving bag-of-features for large scale image search. Int J Comput Vis 87(3):316\u2013336","journal-title":"Int J Comput Vis"},{"key":"11170_CR15","doi-asserted-by":"crossref","unstructured":"Jiang X, Deng X (2022) Knowledge reverse distillation based confidence calibration for deep neural networks. Neural Process Lett, 1\u201316","DOI":"10.1007\/s11063-022-10885-8"},{"issue":"4","key":"11170_CR16","doi-asserted-by":"publisher","first-page":"1297","DOI":"10.1021\/nl904092h","volume":"10","author":"SH Jo","year":"2010","unstructured":"Jo SH, Chang T, Ebong I et al (2010) Nanoscale memristor device as synapse in neuromorphic systems. Nano Lett 10(4):1297\u20131301","journal-title":"Nano Lett"},{"key":"11170_CR17","doi-asserted-by":"crossref","unstructured":"Jouppi NP, Young C, Patil N, et\u00a0al (2017) In-datacenter performance analysis of a tensor processing unit. In: Proceedings of the ACM\/IEEE annual international symposium on computer architecture, pp 1\u201312","DOI":"10.1145\/3079856.3080246"},{"key":"11170_CR18","unstructured":"Kingma DP, Ba J (2014) Adam: a method for stochastic optimization. arXiv:1412.6980"},{"key":"11170_CR19","unstructured":"Krizhevsky A, Hinton G, et\u00a0al (2009) Learning multiple layers of features from tiny images. Technical Report"},{"issue":"7553","key":"11170_CR20","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","journal-title":"Nature"},{"key":"11170_CR21","doi-asserted-by":"publisher","first-page":"4735","DOI":"10.1109\/TIP.2021.3066051","volume":"30","author":"X Li","year":"2021","unstructured":"Li X, Li S, Omar B et al (2021) Reskd: residual-guided knowledge distillation. IEEE Trans Image Process 30:4735\u20134746","journal-title":"IEEE Trans Image Process"},{"issue":"6406","key":"11170_CR22","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 et al (2018) All-optical machine learning using diffractive deep neural networks. Science 361(6406):1004\u20131008","journal-title":"Science"},{"key":"11170_CR23","doi-asserted-by":"crossref","unstructured":"Mirzadeh SI, Farajtabar M, Li A, et\u00a0al (2020) Improved knowledge distillation via teacher assistant. In: Proceedings of the AAAI conference on artificial intelligence, pp 5191\u20135198","DOI":"10.1609\/aaai.v34i04.5963"},{"issue":"7","key":"11170_CR24","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 et al (2019) An all-optical neuron with sigmoid activation function. Opt Express 27(7):9620\u20139630","journal-title":"Opt Express"},{"issue":"7","key":"11170_CR25","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 et al (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"},{"key":"11170_CR26","doi-asserted-by":"crossref","unstructured":"Oikonomou A, Kirtas M, Passalis N, et\u00a0al (2022) A robust, quantization-aware training method for photonic neural networks. In: International conference on engineering applications of neural networks, pp 427\u2013438","DOI":"10.1007\/978-3-031-08223-8_35"},{"key":"11170_CR27","doi-asserted-by":"crossref","unstructured":"Paolini E, De\u00a0Marinis L, Cococcioni M, et\u00a0al (2022) Photonic-aware neural networks. Neural Comput Appl, 1\u201313","DOI":"10.1007\/s00521-022-07243-z"},{"key":"11170_CR28","doi-asserted-by":"crossref","unstructured":"Park W, Kim D, Lu Y, et\u00a0al (2019) Relational knowledge distillation. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 3967\u20133976","DOI":"10.1109\/CVPR.2019.00409"},{"key":"11170_CR29","doi-asserted-by":"crossref","unstructured":"Passalis N, Tefas A (2017a) Learning bag-of-features pooling for deep convolutional neural networks. In: Proceedings of the IEEE conference on computer vision, pp 5755\u20135763","DOI":"10.1109\/ICCV.2017.614"},{"key":"11170_CR30","doi-asserted-by":"publisher","first-page":"277","DOI":"10.1016\/j.patcog.2016.11.014","volume":"64","author":"N Passalis","year":"2017","unstructured":"Passalis N, Tefas A (2017) Neural bag-of-features learning. Pattern Recogn 64:277\u2013294","journal-title":"Pattern Recogn"},{"key":"11170_CR31","doi-asserted-by":"crossref","unstructured":"Passalis N, Tefas A (2018) Learning deep representations with probabilistic knowledge transfer. In: Proceedings of the European conference on computer vision, pp 268\u2013284","DOI":"10.1007\/978-3-030-01252-6_17"},{"key":"11170_CR32","unstructured":"Passalis N, Mourgias-Alexandris G, Tsakyridis A, et\u00a0al (2019) Training deep photonic convolutional neural networks with sinusoidal activations. IEEE Trans Emerg Top Comput Intell"},{"key":"11170_CR33","doi-asserted-by":"crossref","unstructured":"Passalis N, Mourgias-Alexandris G, Pleros N, et\u00a0al (2020a) Adaptive initialization for recurrent photonic networks using sigmoidal activations. In: Proceedings of the IEEE international symposium on circuits and systems, pp 1\u20135","DOI":"10.1109\/ISCAS45731.2020.9181106"},{"key":"11170_CR34","doi-asserted-by":"publisher","first-page":"103","DOI":"10.1016\/j.neunet.2020.05.024","volume":"129","author":"N Passalis","year":"2020","unstructured":"Passalis N, Mourgias-Alexandris G, Pleros N et al (2020) Initializing photonic feed-forward neural networks using auxiliary tasks. Neural Netw 129:103\u2013108","journal-title":"Neural Netw"},{"key":"11170_CR35","doi-asserted-by":"crossref","unstructured":"Passalis N, Tzelepi M, Tefas A (2020c) Heterogeneous knowledge distillation using information flow modeling. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 2339\u20132348","DOI":"10.1109\/CVPR42600.2020.00241"},{"key":"11170_CR36","doi-asserted-by":"crossref","unstructured":"Passalis N, Kirtas M, Mourgias-Alexandris G, et\u00a0al (2021) Training noise-resilient recurrent photonic networks for financial time series analysis. In: Proceedings of the European signal processing conference, pp 1556\u20131560","DOI":"10.23919\/Eusipco47968.2020.9287649"},{"key":"11170_CR37","unstructured":"Romero A, Ballas N, Kahou SE, et\u00a0al (2014) Fitnets: hints for thin deep nets. arXiv:1412.6550"},{"key":"11170_CR38","doi-asserted-by":"crossref","unstructured":"Sivic J, Zisserman A (2003) Video google: A text retrieval approach to object matching in videos. In: IEEE international conference on computer vision, pp 1470\u20131470","DOI":"10.1109\/ICCV.2003.1238663"},{"issue":"1","key":"11170_CR39","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/s41598-017-07754-z","volume":"7","author":"AN Tait","year":"2017","unstructured":"Tait AN, De Lima TF, Zhou E et al (2017) Neuromorphic photonic networks using silicon photonic weight banks. Sci Rep 7(1):1\u201310","journal-title":"Sci Rep"},{"key":"11170_CR40","unstructured":"Tian Y, Krishnan D, Isola P (2019) Contrastive representation distillation. arXiv:1910.10699"},{"issue":"5","key":"11170_CR41","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 et al (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"},{"key":"11170_CR42","doi-asserted-by":"crossref","unstructured":"Tung F, Mori G (2019) Similarity-preserving knowledge distillation. In: Proceedings of the IEEE\/CVF international conference on computer vision, pp 1365\u20131374","DOI":"10.1109\/ICCV.2019.00145"},{"issue":"2","key":"11170_CR43","doi-asserted-by":"publisher","first-page":"191","DOI":"10.1109\/TETCI.2019.2897815","volume":"5","author":"M Tzelepi","year":"2019","unstructured":"Tzelepi M, Tefas A (2019) Graph embedded convolutional neural networks in human crowd detection for drone flight safety. IEEE Trans Emerg Top Comput Intell 5(2):191\u2013204","journal-title":"IEEE Trans Emerg Top Comput Intell"},{"key":"11170_CR44","doi-asserted-by":"crossref","unstructured":"Yim J, Joo D, Bae J, et\u00a0al (2017) A gift from knowledge distillation: fast optimization, network minimization and transfer learning. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 4133\u20134141","DOI":"10.1109\/CVPR.2017.754"},{"key":"11170_CR45","doi-asserted-by":"crossref","unstructured":"Yun S, Park J, Lee K, et\u00a0al (2020) Regularizing class-wise predictions via self-knowledge distillation. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 13,876\u201313,885","DOI":"10.1109\/CVPR42600.2020.01389"},{"key":"11170_CR46","unstructured":"Zagoruyko S, Komodakis N (2016) Paying more attention to attention: improving the performance of convolutional neural networks via attention transfer. arXiv:1612.03928"},{"key":"11170_CR47","doi-asserted-by":"crossref","unstructured":"Zhang L, Song J, Gao A, et\u00a0al (2019) Be your own teacher: improve the performance of convolutional neural networks via self distillation. In: Proceedings of the IEEE\/CVF international conference on computer vision, pp 3713\u20133722","DOI":"10.1109\/ICCV.2019.00381"},{"key":"11170_CR48","doi-asserted-by":"crossref","unstructured":"Zhang Y, Xiang T, Hospedales TM, et\u00a0al (2018) Deep mutual learning. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 4320\u20134328","DOI":"10.1109\/CVPR.2018.00454"},{"key":"11170_CR49","doi-asserted-by":"crossref","unstructured":"Zhao B, Cui Q, Song R, et\u00a0al (2022) Decoupled knowledge distillation. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 11,953\u201311,962","DOI":"10.1109\/CVPR52688.2022.01165"}],"container-title":["Neural Processing Letters"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11063-023-11170-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11063-023-11170-y\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11063-023-11170-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,11]],"date-time":"2023-11-11T17:06:20Z","timestamp":1699722380000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11063-023-11170-y"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,2,24]]},"references-count":49,"journal-issue":{"issue":"7","published-print":{"date-parts":[[2023,12]]}},"alternative-id":["11170"],"URL":"https:\/\/doi.org\/10.1007\/s11063-023-11170-y","relation":{},"ISSN":["1370-4621","1573-773X"],"issn-type":[{"value":"1370-4621","type":"print"},{"value":"1573-773X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,2,24]]},"assertion":[{"value":"1 February 2023","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"24 February 2023","order":2,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare no competing interests.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}]}}