Ensemble learning of diffractive optical networks

Md Sadman Sakib Rahman; Jingxi Li; Deniz Mengu; Yair Rivenson; Aydogan Ozcan

doi:10.1038/s41377-020-00446-w

Go to Nature Website

Your Location：

Home >

Browse articles >

Ensemble learning of diffractive optical networks

Articles

- Ensemble learning of diffractive optical networks
- Light: Science & Applications Vol. 10, Issue 1, Pages: 123-135(2021)
- Affiliations：
  
  1.Electrical and Computer Engineering Department, University of California, Los Angeles, CA 90095, USA
  2.Bioengineering Department, University of California, Los Angeles, CA 90095, USA
  3.California NanoSystems Institute (CNSI), University of California, Los Angeles, CA 90095, USA
- Author bio：
  
  Aydogan Ozcan (ozcan@ucla.edu)
- Funds：
- DOI：10.1038/s41377-020-00446-w
  CLC：
- Published：2021，
  
  Published Online：11 January 2021，
  
  Received：09 September 2020，
  
  Revised：27 November 2020，
  
  Accepted：30 November 2020
- Accepted：
Scan QR Code
Rahman, M. S. S. et al. Ensemble learning of diffractive optical networks. Light: Science & Applications, 10, 123-135 (2021).
DOI：

Rahman, M. S. S. et al. Ensemble learning of diffractive optical networks. Light: Science & Applications, 10, 123-135 (2021). DOI： 10.1038/s41377-020-00446-w.

摘要

Abstract

A plethora of research advances have emerged in the fields of optics and photonics that benefit from harnessing the power of machine learning. Specifically

there has been a revival of interest in optical computing hardware due to its potential advantages for machine learning tasks in terms of parallelization

power efficiency and computation speed. Diffractive deep neural networks (D

NNs) form such an optical computing framework that benefits from deep learning-based design of successive diffractive layers to all-optically process information as the input light diffracts through these passive layers. D

NNs have demonstrated success in vari

ous tasks

including object classification

the spectral encoding of information

optical pulse shaping and imaging. Here

we substantially improve the inference performance of diffractive optical networks using feature engineering and ensemble learning. After independently training 1252 D

NNs that were diversely engineered with a variety of passive input filters

we applied a pruning algorithm to select an optimized ensemble of D

NNs that collectively improved the image classification accuracy. Through this pruning

we numerically demonstrated that ensembles of

= 14 and

= 30 D

NNs achieve blind testing accuracies of 61.14 ± 0.23% and 62.13 ± 0.05%

respectively

on the classification of CIFAR-10 test images

providing an inference improvement of

16% compared to the average performance of the individual D

NNs within each ensemble. These results constitute the highest inference accuracies achieved to date by any diffractive optical neural network design on the same dataset and might provide a significant leap to extend the application space of diffractive optical image classification and machine vision systems.

关键词

Keywords

references

LeCun, Y., Bengio, Y.&Hinton, G. Deep learning.Nature521, 436-444 (2015)..

Krizhevsky, A. , Sutskever, I.&Hinton, G. E. ImageNet classification with deep convolutional neural networks.Commun. ACM60, 84-90 (2017)..

He, K. M. et al. Deep residual learning for image recognition. In2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 770-778 (IEEE, Las Vegas, 2016).

Redmon, J. et al. You only look once: unified, real-time object detection. In2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 779-788 (IEEE, Las Vegas 2016).

Collobert, R.&Weston, J. A unified architecture for natural language processing: deep neural networks with multitask learning. InProc. 25th International Conference on Machine Learning. 160-167 (ACM, New York, 2008).

Sainath, T. N. et al. Deep convolutional neural networks for LVCSR. In2013 IEEE International Conference on Acoustics, Speech and Signal Processing. 8614-8618 (IEEE, Vancouver, 2013).

Xiong, H. Y. et al. The human splicing code reveals new insights into the genetic determinants of disease.Science347, 1254806 (2015)..

Rivenson, Y. et al. Deep learning microscopy.Optica4, 1437-1443 (2017)..

Wang, H. D. et al. Deep learning enables cross-modality super-resolution in fluorescence microscopy.Nat. Methods16, 103-110 (2019)..

Wu, Y. C. et al. Extended depth-of-field in holographic imaging using deep-learning-based autofocusing and phase recovery.Optica5, 704-710 (2018)..

Rivenson, Y. , Wu, Y. C.&Ozcan, A. Deep learning in holography and coherent imaging.Light. : Sci. Appl.8, 85 (2019)..

Barbastathis, G. , Ozcan, A.&Situ, G. On the use of deep learning for computational imaging.Optica6, 921-943 (2019)..

Ballard, Z. S. et al. Deep learning-enabled point-of-care sensing using multiplexed paper-based sensors.npj Digital Med.3, 66 (2020)..

Shinde, P. P.&Shah, S. A review of machine learning and deep learning applications.2018 Fourth International Conference on Computing Communication Control and Automation (ICCUBEA). 1-6 (IEEE, Pune, 2018).

Psaltis, D. et al. Holography in artificial neural networks.Nature343, 325-330 (1990)..

Shen, Y. C. et al. Deep learning with coherent nanophotonic circuits.Nat. Photonics11, 441-446 (2017)..

Tait, A. N. et al. Neuromorphic photonic networks using silicon photonic weight banks.Sci. Rep.7, 7430 (2017)..

Lin, X. et al. All-optical machine learning using diffractive deep neural networks.Science361, 1004-1008 (2018)..

Chang, J. L. et al. Hybrid optical-electronic convolutional neural networks with optimized diffractive optics for image classification.Sci. Rep.8, 12324 (2018)..

Bueno, J. et al. Reinforcement learning in a large-scale photonic recurrent neural network.Optica5, 756-760 (2018)..

Hughes, T. W. et al. Training of photonic neural networks through in situ backpropagation and gradient measurement.Optica5, 864-871 (2018)..

Hughes, T. W. et al. Wave physics as an analog recurrent neural network.Sci. Adv.5, eaay6946 (2019)..

Yan, T. et al. Fourier-space diffractive deep neural network.Phys. Rev. Lett.123, 023901 (2019)..

Feldmann, J. et al. All-optical spiking neurosynaptic networks with self-learning capabilities.Nature569, 208-214 (2019)..

Mengu, D. et al. Analysis of diffractive optical neural networks and their integration with electronic neural networks.IEEE J. Sel. Top. Quantum Electron.26, 3700114 (2020)..

Dou, H. K. et al. Residual D2NN: training diffractive deep neural networks via learnable light shortcuts.Opt. Lett.45, 2688-2691 (2020)..

Ong, J. R. et al. Photonic convolutional neural networks using integrated diffractive optics.IEEE J. Sel. Top. Quantum Electron.26, 7702108 (2020)..

Pai, S. et al. Parallel programming of an arbitrary feedforward photonic network.IEEE J. Sel. Top. Quantum Electron.26, 6100813 (2020)..

Li, J. X. et al. Class-specific differential detection in diffractive optical neural networks improves inference accuracy.Adv. Photonics1, 046001 (2019)..

Luo, Y. et al. Design of task-specific optical systems using broadband diffractive neural networks.Light. Sci. Appl.8, 112 (2019)..

Mengu, D. et al. Misalignment resilient diffractive optical networks.Nanophotonics9, 4207 (2020)..

Veli, M. et al. Terahertz Pulse Shaping Using Diffractive Surfaces.Nat. Commun.https://doi.org/10.1038/s41467-020-20268-zhttps://doi.org/10.1038/s41467-020-20268-z(2021)..

Li, J. X. et al. Machine vision using diffractive spectral encoding. preprint athttps://arxiv.org/abs/2005.11387https://arxiv.org/abs/2005.11387(2020).

Kulce, O. et al. All-Optical Information Processing Capacity of Diffractive Surfaces.Light. Sci. Appl.https://doi.org/10.1038/s41377-020-00439-9https://doi.org/10.1038/s41377-020-00439-9(2021)..

Krizhevsky, A.Learning Multiple Layers of Features from Tiny Images. Technical report (University of Toronto, 2009).

Vilalta, R.&Drissi, Y. A perspective view and survey of meta-learning.Artif. Intell. Rev.18, 77-95 (2002)..

Sagi, O.&Rokach, L. Ensemble learning: a survey.WIREs Data Min. Knowl. Discov.8, e1249 (2018)..

Bahdanau, D. et al. Neural machine translation by jointly learning to align and translate. InProc. International Conference on Learning Representations(2015).

Suthaharan, S. inMachine Learning Models and Algorithms for Big Data Classification: Thinking with Examples for Effective Learning(ed Suthaharan, S. ) 207-235 (Boston: Springer US, 2016).

Lecun, Y. et al. Gradient-based learning applied to document recognition.Proc. IEEE86, 2278-2324 (1998)..

Soifer, V. A. Diffractive nanophotonics and advanced information technologies.Her. Russian Acad. Sci.84, 9-20 (2014)..

Niesler, F.&Hermatschweiler, M. Two-photon polymerization—a versatile microfabrication tool.Laser Technik J.12, 44-47 (2015)..

Geng, Q. et al. Ultrafast multi-focus 3-D nano-fabrication based on two-photon polymerization.Nat. Commun.10, 2179 (2019)..

Yao, P. et al. Multilayer three-dimensional photolithography with traditional planar method.Appl. Phys. Lett.85, 3920-3922 (2004)..

Zhang, C. et al. Printed photonic elements: nanoimprinting and beyond.J. Mater. Chem. C4, 5133-5153 (2016)..

Chen, I. T. et al. Continuous roll-to-roll patterning of three-dimensional periodic nanostructures.Microsyst. Nanoeng.6, 22 (2020)..

Chen, W. T. , Zhu, A. Y.&Capasso, F. Flat optics with dispersion-engineered metasurfaces.Nat. Rev. Mater.5, 604-620 (2020)..

Engelberg, J.&Levy, U. The advantages of metalenses over diffractive lenses.Nat. Commun.11, 1991 (2020)..

Hinton, G. et al. Distilling the knowledge in a neural network. InNIPS 2014 Deep Learning and Representation Learning Workshop(2015).

Kingma, D. et al. Adam: a method for stochastic optimization. InProc. International Conference on Learning Representations(2015).

Views

Downloads

CSCD

Alert me when the article has been cited

Submit

Tools

Publicity Resources

No data

Related Author

No data

Related Institution

No data

⁰