The DOI matches its Crossref record; 57 of the 57 references it cites were found in a registry or an index.
Experimentally realized in situ backpropagation for deep learning in photonic neural networks
Open accessAbstract
Integrated photonic neural networks provide a promising platform for energy-efficient, high-throughput machine learning with extensive scientific and commercial applications. Photonic neural networks efficiently transform optically encoded inputs using Mach-Zehnder interferometer mesh networks interleaved with nonlinearities. We experimentally trained a three-layer, four-port silicon photonic neural network with programmable phase shifters and optical power monitoring to solve classification tasks using “in situ backpropagation,” a photonic analog of the most popular method to train conventional neural networks. We measured backpropagated gradients for phase-shifter voltages by interfering forward- and backward-propagating light and simulated in situ backpropagation for 64-port photonic neural networks trained on MNIST image recognition given errors. All experiments performed comparably to digital simulations ( > 94% test accuracy), and energy scaling analysis indicated a route to scalable machine learning.
Overview
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Adam: A Method for Stochastic Optimization
Kingma, D. P., & Ba, J. (2014) · arXiv · doi:10.48550/arxiv.1412.6980 · Cited by 98,946
Scikit-learn: Machine Learning in Python
Pedregosa, F., Varoquaux, G., Gramfort, A., Michel, V., Thirion, B., Grisel, O., Blondel, M., Müller, A., Nothman, J., Louppe, G., et al. (2012) · arXiv · doi:10.48550/arxiv.1201.0490 · Cited by 71,016
ImageNet: A large-scale hierarchical image database
Deng, J., Dong, W., Socher, R., Li, L.-J., Li, K., & Fei-Fei, L. (2009) · 2009 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2009.5206848 · Cited by 65,333
Learning representations by back-propagating errors
Rumelhart, D. E., Hinton, G. E., & Williams, R. J. (1986) · Nature · doi:10.1038/323533a0 · Cited by 31,892
The MNIST Database of Handwritten Digit Images for Machine Learning Research [Best of the Web]
Deng, L. (2012) · IEEE Signal Processing Magazine · doi:10.1109/msp.2012.2211477 · Cited by 4,836
Deep learning with coherent nanophotonic circuits
Shen, Y., Harris, N. C., Skirlo, S., Prabhu, M., Baehr-Jones, T., Hochberg, M., Sun, X., Zhao, S., Larochelle, H., Englund, D., et al. (2017) · Nature Photonics · doi:10.1038/nphoton.2017.93 · Cited by 3,340
Experimental realization of any discrete unitary operator
Reck, M., Zeilinger, A., Bernstein, H. J., & Bertani, P. (1994) · Physical Review Letters · doi:10.1103/physrevlett.73.58 · Cited by 2,155
1.1 Computing's energy problem (and what we can do about it)
Horowitz, M. (2014) · 2014 IEEE International Solid-State Circuits Conference Digest of Technical Papers (ISSCC) · doi:10.1109/isscc.2014.6757323 · Cited by 2,069
Phase-change materials for non-volatile photonic applications
Wuttig, M., Bhaskaran, H., & Taubner, T. (2017) · Nature Photonics · doi:10.1038/nphoton.2017.126 · Cited by 1,413
Programmable photonic circuits
Bogaerts, W., Pérez, D., Capmany, J., Miller, D. A. B., Poon, J., Englund, D., Morichetti, F., & Melloni, A. (2020) · Nature · doi:10.1038/s41586-020-2764-0 · Cited by 1,368
Self-citationOptimal design for universal multiport interferometers
Clements, W. R., Humphreys, P. C., Metcalf, B. J., Kolthammer, W. S., & Walsmley, I. A. (2016) · Optica · doi:10.1364/optica.3.001460 · Cited by 1,216
Carolan, J., Harrold, C., Sparrow, C., Martín-López, E., Russell, N. J., Silverstone, J. W., Shadbolt, P. J., Matsuda, N., Oguma, M., Itoh, M., et al. (2015) · Science · doi:10.1126/science.aab3642 · Cited by 1,093
Deep physical neural networks trained with backpropagation
Wright, L. G., Onodera, T., Stein, M. M., Wang, T., Schachter, D. T., Hu, Z., & McMahon, P. L. (2022) · Nature · doi:10.1038/s41586-021-04223-6 · Cited by 727
Attojoule Optoelectronics for Low-Energy Information Processing and Communications
Miller, D. A. B. (2017) · Journal of Lightwave Technology · doi:10.1109/jlt.2017.2647779 · Cited by 708
Self-citationAn optical neural chip for implementing complex-valued neural network
Zhang, H., Gu, M., Jiang, X. D., Thompson, J., Cai, H., Paesani, S., Santagati, R., Laing, A., Zhang, Y., Yung, M. H., et al. (2021) · Nature Communications · doi:10.1038/s41467-020-20719-7 · Cited by 666
Nanophotonic lithium niobate electro-optic modulators
Wang, C., Zhang, M., Stern, B., Lipson, M., & Lončar, M. (2018) · Optics Express · doi:10.1364/oe.26.001547 · Cited by 652
Monolithic germanium/silicon avalanche photodiodes with 340 GHz gain–bandwidth product
Kang, Y., Liu, H.-D., Morse, M., Paniccia, M. J., Zadka, M., Litski, S., Sarid, G., Pauchard, A., Kuo, Y.-H., Chen, H.-W., et al. (2009) · Nature Photonics · doi:10.1038/nphoton.2008.247 · Cited by 608
Multipurpose silicon photonics signal processor core
Pérez, D., Gasulla, I., Crudgington, L., Thomson, D. J., Khokhar, A. Z., Li, K., Cao, W., Mashanovich, G. Z., & Capmany, J. (2017) · Nature Communications · doi:10.1038/s41467-017-00714-1 · Cited by 530
Training of photonic neural networks through in situ backpropagation and gradient measurement
Hughes, T. W., Minkov, M., Shi, Y., & Fan, S. (2018) · Optica · doi:10.1364/optica.5.000864 · Cited by 504
Self-citationSelf-configuring universal linear optical component [Invited]
Miller, D. A. B. (2013) · Photonics Research · doi:10.1364/prj.1.000001 · Cited by 474
Self-citationEfficient, compact and low loss thermo-optic phase shifter in silicon
Harris, N. C., Ma, Y., Mower, J., Baehr-Jones, T., Englund, D., Hochberg, M., & Galland, C. (2014) · Optics Express · doi:10.1364/oe.22.010487 · Cited by 427
Linear programmable nanophotonic processors
Harris, N. C., Carolan, J., Bunandar, D., Prabhu, M., Hochberg, M., Baehr-Jones, T., Fanto, M. L., Smith, A. M., Tison, C. C., Alsing, P. M., et al. (2018) · Optica · doi:10.1364/optica.5.001623 · Cited by 396
Large-Scale Optical Neural Networks Based on Photoelectric Multiplication
Hamerly, R., Bernstein, L., Sludds, A., Soljačić, M., & Englund, D. (2019) · Physical Review X · doi:10.1103/physrevx.9.021032 · Cited by 388
Compute Trends Across Three Eras of Machine Learning
Sevilla, J., Heim, L., Ho, A., Besiroglu, T., Hobbhahn, M., & Villalobos, P. (2022) · 2022 International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn55064.2022.9891914 · Cited by 363
Reprogrammable Electro-Optic Nonlinear Activation Functions for Optical Neural Networks
Williamson, I. A. D., Hughes, T. W., Minkov, M., Bartlett, B., Pai, S., & Fan, S. (2020) · IEEE Journal of Selected Topics in Quantum Electronics · doi:10.1109/jstqe.2019.2930455 · Cited by 346
Self-citationPerfect optics with imperfect components
Miller, D. A. B. (2015) · Optica · doi:10.1364/optica.2.000747 · Cited by 327
Self-citationTaylor expansion of the accumulated rounding error
Linnainmaa, S. (1976) · BIT · doi:10.1007/bf01931367 · Cited by 315
Photonic Multiply-Accumulate Operations for Neural Networks
Nahmias, M. A., de Lima, T. F., Tait, A. N., Peng, H.-T., Shastri, B. J., & Prucnal, P. R. (2020) · IEEE Journal of Selected Topics in Quantum Electronics · doi:10.1109/jstqe.2019.2941485 · Cited by 301
Active Silicon Integrated Nanophotonics: Ferroelectric BaTiO3 Devices
Xiong, C., Pernice, W. H. P., Ngai, J. H., Reiner, J. W., Kumah, D., Walker, F. J., Ahn, C. H., & Tang, H. X. (2014) · Nano Letters · doi:10.1021/nl404513p · Cited by 291
Direct Feedback Alignment Provides Learning in Deep Neural Networks
Nøkland, A. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1609.01596 · Cited by 275
Unscrambling light—automatically undoing strong mixing between modes
Annoni, A., Guglielmi, E., Carminati, M., Ferrari, G., Sampietro, M., Miller, D. A., Melloni, A., & Morichetti, F. (2017) · Light: Science & Applications · doi:10.1038/lsa.2017.110 · Cited by 221
Self-citationSelf-aligning universal beam coupler
Miller, D. A. B. (2013) · Optics Express · doi:10.1364/oe.21.006360 · Cited by 196
Self-citationMatrix Optimization on Universal Unitary Photonic Devices
Pai, S., Bartlett, B., Solgaard, O., & Miller, D. A. B. (2019) · Physical Review Applied · doi:10.1103/physrevapplied.11.064044 · Cited by 170
Self-citationMixed-Signal Computing for Deep Neural Network Inference
Murmann, B. (2021) · IEEE Transactions on Very Large Scale Integration (VLSI) Systems · doi:10.1109/tvlsi.2020.3020286 · Cited by 160
MEMS for Photonic Integrated Circuits
Errando-Herranz, C., Takabayashi, A. Y., Edinger, P., Sattari, H., Gylfason, K. B., & Quack, N. (2019) · IEEE Journal of Selected Topics in Quantum Electronics · doi:10.1109/jstqe.2019.2943384 · Cited by 159
Non-Invasive On-Chip Light Observation by Contactless Waveguide Conductivity Monitoring
Morichetti, F., Grillanda, S., Carminati, M., Ferrari, G., Sampietro, M., Strain, M. J., Sorel, M., & Melloni, A. (2014) · IEEE Journal of Selected Topics in Quantum Electronics · doi:10.1109/jstqe.2014.2300046 · Cited by 158
Self-citationEfficient On-Chip Training of Optical Neural Networks Using Genetic Algorithm
Zhang, H., Thompson, J. E., Gu, M., Jiang, X. D., Cai, H. N., Liu, P. Y., Shi, Y., Zhang, Y., Karim, M. F., Lo, G. Q., et al. (2021) · ACS Photonics · doi:10.1021/acsphotonics.1c00035 · Cited by 149
A Fast Stochastic Error-Descent Algorithm for Supervised Learning and Optimization
Cauwenberghs, G. (1992) · CaltechAUTHORS (California Institute of Technology) · Cited by 144
Accelerating recurrent Ising machines in photonic integrated circuits
Prabhu, M., Roques‐Carmes, C., Shen, Y., Harris, N. C., Jing, L., Carolan, J., Hamerly, R., Baehr-Jones, T. W., Hochberg, M., Čeperić, V., et al. (2020) · Optica · doi:10.1364/optica.386613 · Cited by 144
Tunable Efficient Unitary Neural Networks (EUNN) and their application to RNNsPreprint
Jing, L., Shen, Y., Dubček, T., Peurifoy, J., Skirlo, S. A., LeCun, Y., Tegmark, M., & Marin Soljacic, A. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1612.05231 · Cited by 121
Silicon photonic architecture for training deep neural networks with direct feedback alignment
Filipovich, M. J., Guo, Z., Al-Qadasi, M., Márquez, B. A., Morison, H., Sorger, V. J., Prucnal, P. R., Shekhar, S., & Shastri, B. J. (2022) · Optica · doi:10.1364/optica.475493 · Cited by 115
High-fidelity quantum state evolution in imperfect photonic integrated circuits
Mower, J., Harris, N. C., Steinbrecher, G. R., Lahini, Y., & Englund, D. R. (2015) · Physical Review A · doi:10.1103/physreva.92.032322 · Cited by 100
Backpropagation through nonlinear units for the all-optical training of neural networks
Guo, X., Barrett, T. D., Wang, Z., & Lvovsky, A. I. (2021) · Photonics Research · doi:10.1364/prj.411104 · Cited by 99
A Parallel Gradient Descent Method for Learning in Analog VLSI Neural Networks
Alspector, J., Meir, R., Yuhas, B. P., Jayakumar, A. K., & Lippe, D. (1992) · neural information processing systems · Cited by 98
Silicon photonic microelectromechanical phase shifters for scalable programmable photonics
Edinger, P., Takabayashi, A. Y., Errando-Herranz, C., Khan, U., Sattari, H., Verheyen, P., Bogaerts, W., Quack, N., & Gylfason, K. B. (2021) · Optics Letters · doi:10.1364/ol.436288 · Cited by 96
Ten-Port Unitary Optical Processor on a Silicon Photonic Chip
Tang, R., Tanomura, R., Tanemura, T., & Nakano, Y. (2021) · ACS Photonics · doi:10.1021/acsphotonics.1c00419 · Cited by 91
Parallel Programming of an Arbitrary Feedforward Photonic Network
Pai, S., Williamson, I. A. D., Hughes, T. W., Minkov, M., Solgaard, O., Fan, S., & Miller, D. A. B. (2020) · IEEE Journal of Selected Topics in Quantum Electronics · doi:10.1109/jstqe.2020.2997849 · Cited by 86
Self-citationHybrid training of optical neural networks
Spall, J. C., Guo, X., & Lvovsky, A. I. (2022) · Optica · doi:10.1364/optica.456108 · Cited by 79
Separating arbitrary free-space beams with an integrated photonic processor
Milanizadeh, M., SeyedinNavadeh, S., Zanetto, F., Grimaldi, V., Vita, C. D., Klitis, C., Sorel, M., Ferrari, G., Miller, D. A. B., Melloni, A. I., et al. (2022) · Light Science & Applications · doi:10.1038/s41377-022-00884-8 · Cited by 78
Self-citationModel-free distributed learning
Dembo, A., & Kailath, T. (1990) · IEEE Transactions on Neural Networks · doi:10.1109/72.80205 · Cited by 76
Analyzing and generating multimode optical fields using self-configuring networks
Miller, D. A. B. (2020) · Optica · doi:10.1364/optica.391592 · Cited by 57
Self-citationSilicon Photonics for Artificial Intelligence Acceleration : HotChips 32
Ramey, C. (2020) · 2020 IEEE Hot Chips 32 Symposium (HCS) · doi:10.1109/hcs49909.2020.9220525 · Cited by 51
Dual slot-mode NOEM phase shifter
Baghdadi, R., Gould, M., Gupta, S., Tymchenko, M., Bunandar, D., Ramey, C., & Harris, N. C. (2021) · Optics Express · doi:10.1364/oe.423949 · Cited by 44
Universal programmable photonic architecture for quantum information processing
Bartlett, B., & Fan, S. (2020) · Physical Review A · doi:10.1103/physreva.101.042319 · Cited by 31
Self-citationExperimental evaluation of digitally verifiable photonic computing for blockchain and cryptocurrency
Pai, S., Park, T., Ball, M., Penkovsky, B., Dubrovsky, M., Abebe, N. S., Milanizadeh, M., Morichetti, F., Melloni, A. I., Fan, S., et al. (2023) · Optica · doi:10.1364/optica.476173 · Cited by 27
Self-citationPower monitoring in a feedforward photonic network using two output detectors
Pai, S., Valdez, C., Park, T., Milanizadeh, M., Morichetti, F., Melloni, A. I., Fan, S., Solgaard, O., & Miller, D. A. B. (2023) · Nanophotonics · doi:10.1515/nanoph-2022-0527 · Cited by 6
Self-citationAn 8 bit 1.73mW 1.25 GS/s Single-Core SAR ADC in 22 nm FDSOI CMOS
Buhr, S., Plíva, J., Schirmer, T., Khafaji, M. M., & Ellinger, F. (2022) · European Microwave Integrated Circuits Conference · doi:10.23919/eumic54520.2022.9923451 · Cited by 3
Cited by
Single chip photonic deep neural network with accelerated training
Bandyopadhyay, S., Sludds, A., Krastanov, S., Hamerly, R., Harris, N., Bunandar, D., Streshinsky, M., Hochberg, M., & Englund, D. (2022) · arXiv · doi:10.48550/arxiv.2208.01623 · Cited by 265
Optical neural networks: progress and challenges
Fu, T., Zhang, J., Sun, R., Huang, Y., Xu, W., Yang, S., Zhu, Z., & Chen, H. (2024) · Light: Science & Applications · doi:10.1038/s41377-024-01590-3 · Cited by 263
Integrated Electro-Optics on Thin-Film Lithium Niobate
Hu, Y., Zhu, D., Lu, S., Zhu, X., Song, Y., Renaud, D., Assumpcao, D., Cheng, R., Xin, C. J., Yeh, M., et al. (2025) · Nature Reviews Physics · doi:10.1038/s42254-025-00825-5 · Cited by 162
Gao, S., Chen, H., Wang, Y., Duan, Z., Zhang, H., Sun, Z., Shen, Y., & Lin, X. (2024) · Light: Science & Applications · doi:10.1038/s41377-024-01511-4 · Cited by 32
Self-citationPolaritonic machine learning for graph-based data analysis
Wang, Y., Scali, S., & Kyriienko, O. (2026) · Physical Review E · doi:10.1103/fgy1-n4vp
Metadata
- Authors
- Pai, S., Sun, Z., Hughes, T. W., Park, T., Bartlett, B., Williamson, I. A. D., Minkov, M., Milanizadeh, M., Abebe, N., Morichetti, F., Melloni, A., Fan, S., Solgaard, O., & Miller, D. A. B.
- Venue
- Science
- Published
- 2023-04-28
- Volume
- 380
- Issue
- 6643
- Pages
- 398-404
- ISSN
- 0036-8075 (ISSN-L)
- 1095-9203
- OpenAlex
- W4367173722
- Cited by
- 331
- References
- 57
- FWCI
- 29.08
- Type
- journal article
- Language
- en
- Open access
- green
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.