On the use of deep neural networks in optical communications.

Information transfer rates in optical communications may be dramatically increased by making use of spatially non-Gaussian states of light. Here, we demonstrate the ability of deep neural networks to classify numerically generated, noisy Laguerre-Gauss modes of up to 100 quanta of orbital angular momentum with near-unity fidelity. The scheme relies only on the intensity profile of the detected modes, allowing for considerable simplification of current measurement schemes required to sort the states containing increasing degrees of orbital angular momentum. We also present results that show the strength of deep neural networks in the classification of experimental superpositions of Laguerre-Gauss modes when the networks are trained solely using simulated images. It is anticipated that these results will allow for an enhancement of current optical communications technologies.

[1]  Masakazu Matsugu,et al.  Subject independent facial expression recognition with robust face detection using a convolutional neural network , 2003, Neural Networks.

[2]  Claudio Moraga,et al.  The Influence of the Sigmoid Function Parameters on the Speed of Backpropagation Learning , 1995, IWANN.

[3]  Haider A. Alwzwazy,et al.  Robust Convolutional Neural Networks for Image Recognition , 2015 .

[4]  Yoshua Bengio,et al.  Deep Sparse Rectifier Neural Networks , 2011, AISTATS.

[5]  Kamaljit Singh Bhatia,et al.  Comparison of QAM and DP-QPSK in a coherent optical communication system , 2014 .

[6]  Generation of amplitude-shift-keying optical signals using silicon microring resonators. , 2010, Optics express.

[7]  Andrew Zisserman,et al.  Very Deep Convolutional Networks for Large-Scale Image Recognition , 2014, ICLR.

[8]  Naftali Tishby,et al.  Deep learning and the information bottleneck principle , 2015, 2015 IEEE Information Theory Workshop (ITW).

[9]  Timothy Doster,et al.  Machine learning approach to OAM beam demultiplexing via convolutional neural networks. , 2017, Applied optics.

[10]  Sanjaya Lohani,et al.  Deep learning as a tool to distinguish between high orbital angular momentum optical modes , 2016, Optical Engineering + Applications.

[11]  D. Gauthier,et al.  High-dimensional quantum cryptography with twisted light , 2014, 1402.7113.

[12]  A. Zeilinger,et al.  Communication with spatially modulated light through turbulent air across Vienna , 2014, 1402.2602.

[13]  Gaël Varoquaux,et al.  Scikit-learn: Machine Learning in Python , 2011, J. Mach. Learn. Res..

[14]  Andrew Forbes,et al.  Realising high-dimensional quantum entanglement with orbital angular momentum , 2013 .

[15]  Jason Weston,et al.  A unified architecture for natural language processing: deep neural networks with multitask learning , 2008, ICML '08.

[16]  A. Forbes,et al.  Orbital-angular-momentum entanglement in turbulence , 2013, 1306.6495.

[17]  Forrest N. Iandola,et al.  SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <1MB model size , 2016, ArXiv.

[18]  C. Paterson,et al.  Atmospheric turbulence and orbital angular momentum of single photons for optical communication. , 2005, Physical review letters.

[19]  A. Willner,et al.  Optical communications using orbital angular momentum beams , 2015 .

[20]  Yoshua Bengio,et al.  Exploring Strategies for Training Deep Neural Networks , 2009, J. Mach. Learn. Res..

[21]  B. Hiesmayr,et al.  Observation of Four-Photon Orbital Angular Momentum Entanglement. , 2015, Physical review letters.

[22]  Norbert Jankowski,et al.  Survey of Neural Transfer Functions , 1999 .

[23]  Robert Fickler,et al.  Quantum Entanglement of High Angular Momenta , 2012, Science.

[24]  Andrew Forbes,et al.  Creation and detection of optical modes with spatial light modulators , 2016 .

[25]  S. Goyal,et al.  Higher-dimensional orbital-angular-momentum-based quantum key distribution with mutually unbiased bases , 2013, 1402.5810.

[26]  S. Barnett,et al.  Free-space information transfer using light beams carrying orbital angular momentum. , 2004, Optics express.

[27]  Hermann Ney,et al.  Cross-entropy vs. squared error training: a theoretical and experimental comparison , 2013, INTERSPEECH.

[28]  A. Vaziri,et al.  Entanglement of the orbital angular momentum states of photons , 2001, Nature.

[29]  James R. Lewis,et al.  When 100% really isn't 100%: improving the accuracy of small-sample estimates of completion rates , 2006 .

[30]  Osamu Hirota,et al.  Theory of Multiplicative Noise Caused by Coupling Loss and Amplitude Vector Rotation in Optical Communication Channels , 1983, IEEE Trans. Commun..

[31]  Alan E. Willner.  Mining the optical bandwidth for a terabit per second , 1997 .

[32]  John Scott Bridle,et al.  Probabilistic Interpretation of Feedforward Classification Network Outputs, with Relationships to Statistical Pattern Recognition , 1989, NATO Neurocomputing.

[33]  Stephen M. Barnett,et al.  Two-photon entanglement of orbital angular momentum states , 2002 .

[34]  A. Agresti,et al.  Approximate is Better than “Exact” for Interval Estimation of Binomial Proportions , 1998 .

[35]  J. P. Woerdman,et al.  Orbital angular momentum of light and the transformation of Laguerre-Gaussian laser modes. , 1992, Physical review. A, Atomic, molecular, and optical physics.

[36]  Gregor Weihs,et al.  Superpositions of the orbital angular momentum for applications in quantum experiments , 2002 .

[37]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

[38]  A. Willner,et al.  Terabit-Scale Orbital Angular Momentum Mode Division Multiplexing in Fibers , 2013, Science.

[39]  A. Willner,et al.  Terabit free-space data transmission employing orbital angular momentum multiplexing , 2012, Nature Photonics.