A Review of Optical Neural Networks

Optical neural network can process information in parallel by using the technology based on free-space and integrated platform. Over the last half century, the development of integrated circuits has been limited by Moore’s law. We know that neural network is based on the digital computer for successive calculation, most of which cannot be made into real-time processing system. Therefore, it is necessary to develop ONN for real-time processing and device miniaturization. In this paper, we review the progress of optical neural networks. Firstly, based on the principle of artificial neural networks, we elaborate the essence of optical matrix multiplier for linear operation. Then we introduce the optical neural network achieved by free-space optical interconnection and waveguide optical interconnection. Finally we talk about the nonlinearity in optical neural networks. With the gradual maturity of nanotechnology and the rapid advancement of silicon photonic integrated circuits, the progress of integrated photonic neural network has been promoted. Therefore, the construction of optical neural network on the future integrated photonic platform has potential application value.

[1]  Aleksandar D Rakić,et al.  Analysis of optical channel cross talk for free-space optical interconnects in the presence of higher-order transverse modes. , 2005, Applied optics.

[2]  Paul R. Prucnal,et al.  Broadcast and Weight: An Integrated Network For Scalable Photonic Spike Processing , 2014, Journal of Lightwave Technology.

[3]  K. Kyuma,et al.  A new approach to a GaAs/AlGaAs optical neurochip with three layered structure , 1989, International 1989 Joint Conference on Neural Networks.

[4]  B Y Gu,et al.  Gerchberg-Saxton and Yang-Gu algorithms for phase retrieval in a nonunitary transform system: a comparison. , 1994, Applied optics.

[5]  Shaohui Li,et al.  High-contrast all optical bistable switching in coupled nonlinear photonic crystal microcavities , 2010 .

[6]  Laurent Larger,et al.  Reinforcement Learning in a large scale photonic Recurrent Neural Network , 2017, Optica.

[7]  J N Lee,et al.  Acoustooptical matrix-vector product processor: implementation issues. , 1989, Applied optics.

[8]  W S McCulloch,et al.  A logical calculus of the ideas immanent in nervous activity , 1990, The Philosophy of Artificial Intelligence.

[9]  Paul R. Prucnal,et al.  Progress in neuromorphic photonics , 2017 .

[10]  Paul R Prucnal,et al.  A high performance photonic pulse processing device. , 2009, Optics express.

[11]  T. S. Key,et al.  Electronic lighting interference , 1998 .

[12]  J J Hopfield,et al.  Neural networks and physical systems with emergent collective computational abilities. , 1982, Proceedings of the National Academy of Sciences of the United States of America.

[13]  Harish Bhaskaran,et al.  On-chip photonic synapse , 2017, Science Advances.

[14]  Yang Jian-we.  Parallel Subtraction using LCLV and Lenslet Array in Optical Neural Networks , 1997 .

[15]  H. K. Liu,et al.  An optical inner-product array processor for associative retrieval , 1986, Photonics West - Lasers and Applications in Science and Engineering.

[16]  Gregory R. Steinbrecher,et al.  Quantum transport simulations in a programmable nanophotonic processor , 2015, Nature Photonics.

[17]  Tarek El-Ghazawi,et al.  Attojoule Modulators for Photonic Neuromorphic Computing , 2018, 2018 Conference on Lasers and Electro-Optics (CLEO).

[18]  Guanrong Chen,et al.  Large Memory Capacity in Chaotic Artificial Neural Networks: A View of the Anti-Integrable Limit , 2009, IEEE Transactions on Neural Networks.

[19]  A. P. Knights,et al.  The evolution of silicon photonics as an enabling technology for optical interconnection , 2012 .

[20]  Roberto Morandotti,et al.  On-chip generation of high-dimensional entangled quantum states and their coherent control , 2017, Nature.

[21]  D. Psaltis,et al.  Holography in artificial neural networks , 1990, Nature.

[22]  Jin Zhao,et al.  A new self-learning algorithm of neural networks and its application , 2008, 2008 IEEE International Conference on Industrial Technology.

[23]  Eli Shlizerman,et al.  An Optical Frontend for a Convolutional Neural Network , 2018, Applied optics.

[24]  H. John,et al.  Why future supercomputing requires optics , 2010 .

[25]  Byoungil Lee,et al.  Nanoelectronic programmable synapses based on phase change materials for brain-inspired computing. , 2012, Nano letters.

[26]  D Psaltis,et al.  Optical implementation of the Hopfield model. , 1985, Applied optics.

[27]  C.A.L. Bailer-Jones,et al.  An introduction to artificial neural networks , 2001 .

[28]  Xiujian Li,et al.  Crosstalk analysis of aligned and misaligned free-space optical interconnect systems. , 2010, Journal of the Optical Society of America. A, Optics, image science, and vision.

[29]  Damien Rontani,et al.  All-Optical Reservoir Computing on a Photonic Chip Using Silicon-Based Ring Resonators , 2018, IEEE Journal of Selected Topics in Quantum Electronics.

[30]  B. Hunt.  A matrix theory proof of the discrete convolution theorem , 1971 .

[31]  A. Bianco,et al.  Photopolymeric films with highly tunable refractive index modulation for high precision diffractive optics , 2016 .

[32]  Dirk Englund,et al.  Deep learning with coherent nanophotonic circuits , 2017, 2017 Fifth Berkeley Symposium on Energy Efficient Electronic Systems & Steep Transistors Workshop (E3S).

[33]  J W Goodman,et al.  Fully parallel, high-speed incoherent optical method for performing discrete Fourier transforms. , 1978, Optics letters.

[34]  K. Ang,et al.  2D photonic memristor beyond graphene: progress and prospects , 2020, Nanophotonics.

[35]  James G. King,et al.  Reconstruction and Simulation of Neocortical Microcircuitry , 2015, Cell.

[36]  Daniel Brunner,et al.  Diffractive Coupling For Photonic Networks: How Big Can We Go? , 2019, IEEE Journal of Selected Topics in Quantum Electronics.

[37]  Fabio Sciarrino,et al.  Integrated photonic quantum technologies , 2019, Nature Photonics.

[38]  Ramin Pashaie,et al.  Optical realization of bioinspired spiking neurons in the electron trapping material thin film. , 2007, Applied optics.

[39]  Y Zhang,et al.  Coaxial architecture of an optical neural network with a lenslet array. , 1994, Optics letters.

[40]  K Y Hsu,et al.  Matrix-matrix multiplication by using anisotropic self-diffraction in BaTiO(3). , 1994, Applied optics.

[41]  Dirk Englund,et al.  Quantum optical neural networks , 2018, npj Quantum Information.

[42]  Yue Jiang,et al.  All-optical neural network with nonlinear activation functions , 2019, Optica.

[43]  Dimitris Syvridis,et al.  All-optical reservoir computing system based on InGaAsP ring resonators for high-speed identification and optical routing in optical networks , 2015, SPIE OPTO.

[44]  J. Feldmann,et al.  All-optical spiking neurosynaptic networks with self-learning capabilities , 2019, Nature.

[45]  Yi Luo,et al.  Analysis of Diffractive Optical Neural Networks and Their Integration With Electronic Neural Networks , 2018, IEEE Journal of Selected Topics in Quantum Electronics.

[46]  Volker J. Sorger,et al.  110 Attojoule-per-bit Efficient Graphene-based Plasmon Modulator on Silicon , 2018, 2018 Conference on Lasers and Electro-Optics (CLEO).

[47]  T. Karr,et al.  High-speed spatial light modulator , 1985, IEEE Journal of Quantum Electronics.

[48]  Lianqing Zhu,et al.  Miniaturized Diffraction Grating Design and Processing for Deep Neural Network , 2019, IEEE Photonics Technology Letters.

[49]  Li Fang,et al.  All-optical reservoir computer based on saturation of absorption. , 2014, Optics express.

[50]  Serge Massar,et al.  All-optical Reservoir Computing , 2012, Optics express.

[51]  G. Lynch,et al.  The neurobiology of learning and memory , 1989, Cognition.

[52]  Paul Crozat,et al.  Integrated germanium optical interconnects on silicon substrates , 2014, Nature Photonics.

[53]  Yi Luo,et al.  Design of task-specific optical systems using broadband diffractive neural networks , 2019, Light, science & applications.

[54]  Volker J. Sorger,et al.  Electrooptic nonlinear activation functions for vector matrix multiplications in optical neural networks , 2018 .

[55]  D. Fedyanin,et al.  Lasing threshold of thresholdless and non-thresholdless metal-semiconductor nanolasers. , 2018, Optics express.

[56]  Jian Wang,et al.  Graphene-assisted multiple-input high-base optical computing , 2016, Scientific Reports.

[57]  Tarek El-Ghazawi,et al.  Neuromorphic photonics with electro-absorption modulators. , 2018, Optics express.

[58]  Jianji Dong,et al.  Phosphorene-assisted silicon photonic modulator with fast response time , 2020, Nanophotonics.

[59]  Hsin-Chia Fu,et al.  A Hybrid Neural Network Model for Solving Optimization Problems , 1993, IEEE Trans. Computers.

[60]  Ellen Zhou,et al.  Neuromorphic photonic networks using silicon photonic weight banks , 2017, Scientific Reports.

[61]  H. Tsang,et al.  In-Plane Optical Absorption and Free Carrier Absorption in Graphene-on-Silicon Waveguides , 2014, IEEE Journal of Selected Topics in Quantum Electronics.

[62]  Elizabeth C. Behrman,et al.  Optical neural network using Kerr-type nonlinear materials , 1994, Proceedings of the Fourth International Conference on Microelectronics for Neural Networks and Fuzzy Systems.

[63]  Nicholas T. Carnevale,et al.  The NEURON Simulation Environment , 1997, Neural Computation.

[64]  Lei Ying,et al.  Nanophotonic media for artificial neural inference , 2018, Photonics Research.

[65]  Liu Jin-Yue,et al.  Research on the Non-Linear Function Fitting of RBF Neural Network , 2013, 2013 International Conference on Computational and Information Sciences.

[66]  Yansong Chen,et al.  4f-type optical system for matrix multiplication , 1993 .

[67]  S. Yeh,et al.  Optical implementation of the hopfield neural network with matrix gratings. , 2004, Applied optics.

[68]  D. Pierangeli,et al.  Deep optical neural network by living tumour brain cells. , 2018, 1812.09311.

[69]  Mohamed Chtourou,et al.  A Hybrid Training Algorithm for Feedforward Neural Networks , 2006, Neural Processing Letters.

[70]  Y Zhang,et al.  Implementation of a large-scale optical neural network by use of a coaxial lenslet array for interconnection. , 1997, Applied optics.

[71]  Koji Akiyama,et al.  Optical neural network using vector-feature extraction. , 1993, Applied optics.

[72]  Yi Luo,et al.  All-optical machine learning using diffractive deep neural networks , 2018, Science.

[73]  F T Yu,et al.  Two-dimensional programmable optical neural network. , 1989, Applied optics.

[74]  Chii-Chang Chen,et al.  Optical neural networks based on optical fiber-communication system , 2019, Neurocomputing.

[75]  Steven G. Johnson,et al.  Optimal bistable switching in nonlinear photonic crystals. , 2002, Physical review. E, Statistical, nonlinear, and soft matter physics.

[76]  Mario Miscuglio,et al.  All-optical nonlinear activation function for photonic neural networks [Invited] , 2018, Optical Materials Express.

[77]  C. Wright,et al.  Arithmetic and Biologically-Inspired Computing Using Phase-Change Materials , 2011, Advanced materials.

[78]  J. Rarity,et al.  Photonic quantum technologies , 2009, 1003.3928.

[79]  Shih-Chia Huang,et al.  Radial Basis Function Based Neural Network for Motion Detection in Dynamic Scenes , 2014, IEEE Transactions on Cybernetics.