Comment on All-optical machine learning using diffractive deep neural networks

Lin et al. (Reports, 7 September 2018, p. 1004) reported a remarkable proposal that employs a passive, strictly linear optical setup to perform pattern classifications. But interpreting the multilayer diffractive setup as a deep neural network and advocating it as an all-optical deep learning framework are not well justified and represent a mischaracterization of the system by overlooking its defining characteristics of perfect linearity and strict passivity.

READ FULL TEXT VIEW PDF
POST COMMENT

Comments

There are no comments yet.

Authors

page 1

page 2

page 3

page 4

04/14/2018

All-Optical Machine Learning Using Diffractive Deep Neural Networks

We introduce an all-optical Diffractive Deep Neural Network (D2NN) archi...
10/10/2018

Response to Comment on "All-optical machine learning using diffractive deep neural networks"

In their Comment, Wei et al. (arXiv:1809.08360v1 [cs.LG]) claim that our...
12/23/2019

An optical diffractive deep neural network with multiple frequency-channels

Diffractive deep neural network (DNNet) is a novel machine learning fram...
04/24/2019

Optical machine learning with incoherent light and a single-pixel detector

The concept of optical diffractive neural network (DNN) is proposed rece...
07/01/2020

Deep Neural Networks for Computational Optical Form Measurements

Deep neural networks have been successfully applied in many different fi...
06/08/2019

Class-specific Differential Detection in Diffractive Optical Neural Networks Improves Inference Accuracy

Diffractive deep neural networks have been introduced earlier as an opti...
12/18/2018

Machine Learning for QoT Estimation of Unseen Optical Network States

We apply deep graph convolutional neural networks for Quality-of-Transmi...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.

Disclosure statement

The authors have no potential financial or non-financial conflicts of interest.

Notes on contributors

All authors contributed equally in researching, collating, and writing.

References

  • [1] X. Lin et al., “All-optical machine learning using diffractive deep neural networks,” Science, vol. 361, pp. 1004-1008 (2018).
  • [2] I. Goodfellow, Y. Bengio, and A. Courville, Deep learning (MIT Press, 2016).
  • [3] M. L. Minsky and S. A. Papert, Perceptrons. (MIT Press, 1969).
  • [4] J. W. Goodman, Introduction to Fourier Optics, 3rd Ed. (Roberts & Company Pub., 2005).
  • [5] T. D. Gerke and R. Piestun, “Aperiodic volume optics,” Nature Photon., vol. 4, pp. 188-193 (2010).
  • [6] J.-F. Morizur et al., “Programmable unitary spatial mode manipulation,” J. Opt. Soc. Am. A, vol. 27, no. 11, pp. 2524-2531 (2010).
  • [7] G. Labroille et al., “Efficient and mode selective spatial mode multiplexer based on multi-plane light conversion,” Opt. Exp., vol. 22, no. 13, pp. 15599-15607 (2014).
  • [8] D. A. B. Miller, “All linear optical devices are mode converters ,” Opt. Exp., vol. 20, no. 21, pp. 23985-23993 (2012).
  • [9] Z. I. Borevich and S. L. Krupetskii, “Subgroups of the unitary group that contain the group of diagonal matrices,” J. Soviet Math., vol. 17, 1951-1959 (1981).
  • [10] D. Michie, D. J. Spiegelhalter, and C. C. Taylor (Eds.),

    Machine Learning, Neural and Statistical Classification

    (Ellis Horwood Ltd., 1994).
  • [11] C. M. Bishop, Pattern Recognition and Machine Learning (Springer, 2006).
  • [12] Y. Shen et al., “Deep learning with coherent nanophotonic circuits,” Nature Photon., vol. 11, pp. 441-446 (2017).
  • [13] O. Leclerc, B. Lavigne, D. Chiaroni, and E. Desurvire, “All-optical regeneration: principles and WDM implementation,” Ch. 15 in I. Kaminow and T. Li (Eds.), Optical Fiber Telecommunications IV A: Components (Academic Press, 2002).
  • [14] J.-C. Simon et al., “All-optical regeneration techniques,” Ann. Telecomm., vol. 58, no. 11-12, pp. 1708-1724 (2003).
  • [15] D. S. Abrams and S. Lloyd, “Nonlinear quantum mechanics implies polynomial-time solution for NP-complete and #P problems,” Phys. Rev. Lett., vol. 81, no. 18, pp. 3992-3995 (1998).