Deep-learning-powered photonic analog-to-digital conversion

Shaofu Xu; Xiuting Zou; Bowen Ma; Jianping Chen; Lei Yu; Weiwen Zou

doi:10.1038/s41377-019-0176-4

Go to Nature Website

Your Location：

Home >

Browse articles >

Deep-learning-powered photonic analog-to-digital conversion

Article

- Deep-learning-powered photonic analog-to-digital conversion
- Deep-learning-powered photonic analog-to-digital conversion
- LSA 2019年8卷第4期页码：580-590
- Affiliations：
  
  State Key Laboratory of Advanced Optical Communication Systems and Networks, Intelligent Microwave Lightwave Integration Innovation Center (iMLic), Department of Electronic Engineering, Shanghai Jiao Tong University, 200240 Shanghai, China
- Author bio：
  
  Weiwen Zou (wzou@sjtu.edu.cn)
- Funds：
- DOI：10.1038/s41377-019-0176-4
  中图分类号：
- 纸质出版日期：2019，
  
  网络出版日期：2019-07-17，
  
  收稿日期：2019-03-24，
  
  修回日期：2019-06-19，
  
  录用日期：2019-06-20
- Accepted：
Scan QR Code
Deep-learning-powered photonic analog-to-digital conversion[J]. LSA, 2019,8(4):580-590.

Xu, S. F. et al. Deep-learning-powered photonic analogto-digital conversion. Light: Science & Applications, 8, 580-590 (2019).
Deep-learning-powered photonic analog-to-digital conversion[J]. LSA, 2019,8(4):580-590. DOI： 10.1038/s41377-019-0176-4.

Xu, S. F. et al. Deep-learning-powered photonic analogto-digital conversion. Light: Science & Applications, 8, 580-590 (2019). DOI： 10.1038/s41377-019-0176-4.

摘要

Abstract

Analog-to-digital converters (ADCs) must be high speed

broadband

and accurate for the development of modern information systems

such as radar

imaging

and communications systems; photonic technologies are regarded as promising technologies for realizing these advanced requirements. Here

we present a deep-learning-powered photonic ADC architecture that simultaneously exploits the advantages of electronics and photonics and overcomes the bottlenecks of the two technologies

thereby overcoming the ADC tradeoff among speed

bandwidth

and accuracy. Via supervised training

the adopted deep neural networks learn the patterns of photonic system defects and recover the distorted data

thereby maintaining the high quality of the electronic quantized data succinctly and adaptively. The numerical and experimental results demonstrate that the proposed architecture outperforms state-of-the-art ADCs with developable high throughput; hence

deep learning performs well in photonic ADC systems. We anticipate that the proposed architecture will inspire future high-performance photonic ADC design and provide opportunities for substantial performance enhancement for the next-generation information systems.

关键词

Keywords

references

Andrews, J. G. et al. What will 5G be?IEEE J. Sel. Areas Commun.32, 1065-1082 (2014)..

Zou, W. W. et al. All-optical central-frequency-programmable and bandwidth-tailorable radar.Sci. Rep.6, 19786 (2016)..

Ghelfi, P. et al. A fully photonics-based coherentradar system.Nature507, 341-345 (2014)..

Valley, G. C. Photonic analog-to-digital converters.Opt. Express15, 1955-1982 (2017)..

Khilo, A. et al. Photonic ADC: overcoming the bottleneck of electronic jitter.Opt. Express20, 4454-4469 (2012)..

Yao, J. P. Microwave photonics.J. Light. Technol.27, 314-335 (2009)..

Juodawlkis, P. W. et al. Optically sampled analog-to-digital converters.IEEE Trans. Microw. Theory Tech.49, 1840-1853 (2001)..

Yang, G. et al. Theoretical and experimental analysis of channel mismatch in time-wavelength interleaved optical clock based on mode-locked laser.Opt. Express23, 2174-2186 (2015)..

Yang, G. et al. Compensation of multi-channel mismatches in high-speed high-resolution photonic analog-to-digital converter.Opt. Express24, 24061-24074 (2016)..

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.Adv. Neural Inf. Process. Syst.25, 1097-1105 (2012)..

Tompson, J. et al. Joint training of a convolutional network and a graphical model for human pose estimation.Adv. Neural Inf. Process. Syst.2, 1799-1807 (2014)..

Anthimopoulos, M. et al. Lung pattern classification for interstitial lung diseases using a deep convolutional neural network.IEEE Trans. Med. Imaging35, 1207-1216 (2016)..

Silver, D. et al. Mastering the game of Go without human knowledge.Nature550, 354-359 (2017)..

Lu, X. et al. Speech enhancement based on deep denoising autoencoder. InInterspeech436-440 (2013).

Xie, J., Xu, L.&Chen, E. Image denoising and inpainting with deep neural networks.Adv. Neural Inf. Process. Syst.25, 350-358 (2012)..

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

Zhu, B. et al. Image reconstruction by domain-transform manifold learning.Nature555, 487-492 (2018)..

Won, R. Intelligent learning with light.Nat. Photonics12, 571-573 (2018)..

Wiecha, P. R. et al. Pushing the limits of optical information storage using deep learning.Nat. Nanotechnol.14, 237-244 (2019)..

Pierno, L. et al. Optical switching matrix as time domain demultiplexer in photonic ADC. InProc. 2013 European Microwave Integrated Circuit Conference41-44 (IEEE, 2013).

He, K. M. et al. Deep residual learning for image recognition. InProc. 2016 IEEE Conference on Computer Vision and Pattern Recognition770-778 (IEEE, 2016).

Zhang, K. et al. Beyond a Gaussian denoiser: residual learning of deep CNN for image denoising.IEEE Trans. Image Process.26, 3142-3155 (2017)..

Coates, A. et al. Deep learning with COTS HPC systems. InProc. 30th International Conference on International Conference on Machine Learning28, III-1337-III-1345 (2013)..

Jouppi, N. P. et al. In-datacenter performance analysis of a tensor processing unit.Proc. 44th Annual International Symposium on Computer Architecture1-12 (ACM, 2017).

Ambrogio, S. et al. Equivalent-accuracy accelerated neural-network training using analogue memory.Nature558, 60-67 (2018)..

Shen, Y. C. H. et al. Deep learning with coherent nanophotonic circuits.Nat. Photonics1, 441-446 (2017)..

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

Park, S. C., Park, M. K.&Kang, M. G. Super-resolution image reconstruction: a technical overview.IEEE Signal Process. Mag.20, 21-36 (2003)..

Shi, W. Z. H. et al. Real-time single image and video super-resolution using an efficient sub-pixel convolutional neural network. InProc. IEEE Conference on Computer Vision and Pattern Recognition1874-1883 (IEEE, 2016).

Han, D., Kim, J., Kin J. Deep pyramidal residual networks[EB/OL](2016).https://arxiv.org/abs/1610.02915https://arxiv.org/abs/1610.02915.

He, K. M. et al. Identity mappings in deep residual networks. InProc. 14th European Conference Computer Vision630-645 (Springer, 2016).

Prakash, V. N. V. S., Prasad, K. S.&Prasad, T. J. Deep learning approach for image denoising and image demosaicing.Int. J. Comput. Appl.168, 18-26 (2017)..

IEEE.IEEE Standard for Terminology and Test Methods for Analog-to-Digital Convertershttp://ieeexplore.ieee.org/xpl/articleDetails.jsp?arnumber=929859&contentType=Standardshttp://ieeexplore.ieee.org/xpl/articleDetails.jsp?arnumber=929859&contentType=Standards(2001)..

Klein, S. et al. Adaptive stochastic gradient descent optimisation for image registration.Int. J. Comput. Vis.81, 227-239 (2009)..

Wolpert, D. H.&Macready, W. G. No free lunch theorems for optimization.IEEE Trans. Evolut. Comput.1, 67-82 (1997)..

GPU Specs databasehttps://www.techpowerup.com/gpu-specs/https://www.techpowerup.com/gpu-specs/(2017).

Google. Cloud TPUhttps://cloud.google.com/tpu/https://cloud.google.com/tpu/(2019).

Xilinx Alveo. U200: Adaptable Accelerator Cards for Data Center Workloads.https://www.xilinx.com/publications/product-briefs/alveo-product-brief.pdfhttps://www.xilinx.com/publications/product-briefs/alveo-product-brief.pdf(2018).

浏览量

Downloads

CSCD

文章被引用时，请邮件提醒。

Submit

工具集

关联资源

暂无数据