Perspective on photonic memristive neuromorphic computing

Neuromorphic computing applies concepts extracted from neuroscience to develop devices shaped like neural systems and achieve brain-like capacity and efficiency. In this way, neuromorphic machines, able to learn from the surrounding environment to deduce abstract concepts and to make decisions, promise to start a technological revolution transforming our society and our life. Current electronic implementations of neuromorphic architectures are still far from competing with their biological counterparts in terms of real-time information-processing capabilities, packing density and energy efficiency. A solution to this impasse is represented by the application of photonic principles to the neuromorphic domain creating in this way the field of neuromorphic photonics. This new field combines the advantages of photonics and neuromorphic architectures to build systems with high efficiency, high interconnectivity and high information density, and paves the way to ultrafast, power efficient and low cost and complex signal processing. In this Perspective, we review the rapid development of the neuromorphic computing field both in the electronic and in the photonic domain focusing on the role and the applications of memristors. We discuss the need and the possibility to conceive a photonic memristor and we offer a positive outlook on the challenges and opportunities for the ambitious goal of realising the next generation of full-optical neuromorphic hardware.

[1]  Kaare B. Mikkelsen,et al.  EEG Recorded from the Ear: Characterizing the Ear-EEG Method , 2015, Front. Neurosci..

[2]  E. Pop,et al.  GST-on-silicon hybrid nanophotonic integrated circuits: a non-volatile quasi-continuously reprogrammable platform , 2018 .

[3]  R. Waser,et al.  Nanoionics-based resistive switching memories. , 2007, Nature materials.

[4]  A. Ferrari,et al.  Graphene Photonics and Optoelectroncs , 2010, CLEO 2012.

[5]  Chiara Bartolozzi,et al.  Neuromorphic Electronic Circuits for Building Autonomous Cognitive Systems , 2014, Proceedings of the IEEE.

[6]  Vittorio Dante,et al.  A VLSI recurrent network of integrate-and-fire neurons connected by plastic synapses with long-term memory , 2003, IEEE Trans. Neural Networks.

[7]  B. Cumming,et al.  Tuning the Refractive Index in Gyroid Photonic Crystals via Lead‐Chalcogenide Nanocrystal Coating , 2016 .

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

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

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

[11]  H.-S. Philip Wong,et al.  In-memory computing with resistive switching devices , 2018, Nature Electronics.

[12]  Michal Lipson,et al.  Nonlinear silicon photonics , 2012, 2012 17th Opto-Electronics and Communications Conference.

[13]  Fuxi Gan,et al.  Nonlinear absorption of Sb-based phase change materials due to the weakening of the resonant bond , 2012 .

[14]  Hilde van der Togt,et al.  Publisher's Note , 2003, J. Netw. Comput. Appl..

[15]  Jaime E. Santos,et al.  Optical bistability of graphene in the terahertz range , 2014, 1406.5889.

[16]  Jingsong Wei,et al.  Optical nonlinear absorption characteristics of crystalline Ge2Sb2Te5 thin films , 2011 .

[17]  L. Luo.  Principles of Neurobiology , 2015 .

[18]  L. Y. Chen,et al.  Reproducible unipolar resistance switching in stoichiometric ZrO2 films , 2007 .

[19]  Sadique Sheik,et al.  Editorial: Synaptic Plasticity for Neuromorphic Systems , 2016, Front. Neurosci..

[20]  Weisheng Zhao,et al.  Two‐Terminal Carbon Nanotube Programmable Devices for Adaptive Architectures , 2010, Advanced materials.

[21]  H. Wong,et al.  Cost-effective, transfer-free, flexible resistive random access memory using laser-scribed reduced graphene oxide patterning technology. , 2014, Nano letters.

[22]  Yaoyu Cao,et al.  Three-dimensional deep sub-diffraction optical beam lithography with 9 nm feature size , 2013, Nature Communications.

[23]  Jaroslaw Sotor,et al.  Dissipative soliton generation in Er-doped fiber laser mode-locked by Sb2Te3 topological insulator. , 2015, Optics letters.

[24]  Ali Khiat,et al.  Challenges hindering memristive neuromorphic hardware from going mainstream , 2018, Nature Communications.

[25]  H. Mi,et al.  Graphene/phase change material nanocomposites: light-driven, reversible electrical resistivity regulation via form-stable phase transitions. , 2015, ACS applied materials & interfaces.

[26]  A. Hodgkin,et al.  A quantitative description of membrane current and its application to conduction and excitation in nerve , 1952, The Journal of physiology.

[27]  Carver A. Mead,et al.  Neuromorphic electronic systems , 1990, Proc. IEEE.

[28]  Manish Kumar.  Large-scale neuromorphic computing systems , 2016 .

[29]  Suresh Chandra,et al.  Polarity-dependent memory switching effects in the Ti/CdxPb1-xS/Ag system , 1995 .

[30]  S. Mittal,et al.  Topological Photonic Systems , 2018 .

[31]  Indranil Chakraborty,et al.  Toward Fast Neural Computing using All-Photonic Phase Change Spiking Neurons , 2018, Scientific Reports.

[32]  Shanhui Fan,et al.  Training of Photonic Neural Networks through In Situ Backpropagation , 2018, 2019 Conference on Lasers and Electro-Optics (CLEO).

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

[34]  D Psaltis,et al.  Optical information processing based on an associative-memory model of neural nets with thresholding and feedback. , 1985, Optics letters.

[35]  Qiming Zhang,et al.  Artificial neural networks enabled by nanophotonics , 2019, Light: Science & Applications.

[36]  Bhavin J. Shastri,et al.  Neuromorphic photonic networks using silicon photonic weight banks , 2016, Scientific Reports.

[37]  F. Guinea,et al.  The electronic properties of graphene , 2007, Reviews of Modern Physics.

[38]  Doo Seok Jeong,et al.  Reliability of neuronal information conveyed by unreliable neuristor-based leaky integrate-and-fire neurons: a model study , 2015, Scientific Reports.

[39]  Farnood Merrikh-Bayat,et al.  Training and operation of an integrated neuromorphic network based on metal-oxide memristors , 2014, Nature.

[40]  Xianghan Yao,et al.  Giant optical nonlinearity of graphene in a strong magnetic field , 2011, 2012 Conference on Lasers and Electro-Optics (CLEO).

[41]  C. Peng,et al.  Experimental and theoretical investigations of laser-induced crystallization and amorphization in phase-change optical recording media , 1997 .

[42]  Yan Wang,et al.  Nonlinear optical properties of graphene oxide in nanosecond and picosecond regimes , 2009 .

[43]  Jian Wang,et al.  On-chip silicon photonic signaling and processing: a review. , 2018, Science bulletin.

[44]  Wei Yang Lu,et al.  Nanoscale memristor device as synapse in neuromorphic systems. , 2010, Nano letters.

[45]  Kai Liu,et al.  Ultra-long, free-standing, single-crystalline vanadium dioxide micro/nanowires grown by simple thermal evaporation , 2012 .

[46]  Guigang Zhang,et al.  Deep Learning , 2016, Int. J. Semantic Comput..

[47]  Andrew S. Cassidy,et al.  A million spiking-neuron integrated circuit with a scalable communication network and interface , 2014, Science.

[48]  Masaya Notomi,et al.  Ultralow-power all-optical RAM based on nanocavities , 2012, Nature Photonics.

[49]  Paul V. Braun,et al.  Fabrication of Three‐Dimensional Photonic Crystals Using Multibeam Interference Lithography and Electrodeposition , 2009 .

[50]  A S Spinelli,et al.  Memristive neural network for on-line learning and tracking with brain-inspired spike timing dependent plasticity , 2017, Scientific Reports.

[51]  L. Chua.  Memristor-The missing circuit element , 1971 .

[52]  Saulius Juodkazis,et al.  Sculpturing of photonic crystals by ion beam lithography: towards complete photonic bandgap at visible wavelengths. , 2011, Optics express.

[53]  D. Lynch,et al.  Handbook of Optical Constants of Solids , 1985 .

[54]  J. Grollier,et al.  A ferroelectric memristor. , 2012, Nature materials.

[55]  Jingsong Wei,et al.  Origin of the giant optical nonlinearity of Sb2Te3 phase change materials , 2010 .

[56]  P. Prucnal,et al.  NEUROMORPHIC PHOTONICS , 2017 .

[57]  Manuel Le Gallo,et al.  Stochastic phase-change neurons. , 2016, Nature nanotechnology.

[58]  Doo Seok Jeong,et al.  Relaxation oscillator-realized artificial electronic neurons, their responses, and noise. , 2016, Nanoscale.

[59]  Y. Pershin,et al.  Spin Memristive Systems: Spin Memory Effects in Semiconductor Spintronics , 2008, 0806.2151.

[60]  Ji Zhou,et al.  Microwave Memristive-like Nonlinearity in a Dielectric Metamaterial , 2014, Scientific Reports.

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

[62]  Francis T. S. Yu,et al.  Overview of hybrid optical neural networks , 1996 .

[63]  M. Wuttig,et al.  Phase-change materials for rewriteable data storage. , 2007, Nature materials.

[64]  Kevin J. Miller,et al.  Optical phase change materials in integrated silicon photonic devices: review , 2018, Optical Materials Express.

[65]  Juerg Leuthold,et al.  Optical memristive switches , 2017, Journal of Electroceramics.

[66]  Paul R. Prucnal,et al.  Neuromorphic Photonics , Principles of , 2018 .

[67]  B. Jia,et al.  In Situ Third‐Order Non‐linear Responses During Laser Reduction of Graphene Oxide Thin Films Towards On‐Chip Non‐linear Photonic Devices , 2014, Advanced materials.

[68]  Elisabetta Chicca,et al.  Tunnel junction based memristors as artificial synapses , 2015, Front. Neurosci..

[69]  Chung Lam,et al.  Brain-like associative learning using a nanoscale non-volatile phase change synaptic device array , 2014, Front. Neurosci..

[70]  Haoran Ren,et al.  Optically Digitalized Holography: A Perspective for All-Optical Machine Learning , 2019, Engineering.

[71]  Paul R Prucnal,et al.  Ultrafast all-optical implementation of a leaky integrate-and-fire neuron. , 2011, Optics express.

[72]  Peng Lin,et al.  Fully memristive neural networks for pattern classification with unsupervised learning , 2018 .

[73]  Yannick Bornat,et al.  Analog-digital simulations of full conductance-based networks of spiking neurons with spike timing dependent plasticity , 2006, Network.

[74]  Jean-Pierre Locquet,et al.  Production of VO2 thin films through post-deposition annealing of V2O3 and VOx films , 2015 .

[75]  Demis Hassabis,et al.  Mastering the game of Go with deep neural networks and tree search , 2016, Nature.

[76]  C. David Wright,et al.  Controlled switching of phase-change materials by evanescent-field coupling in integrated photonics [Invited] , 2018, Optical Materials Express.

[77]  Alexandros Emboras,et al.  Nanoscale plasmonic memristor with optical readout functionality. , 2013, Nano letters.

[78]  S. Joshi,et al.  65k-neuron integrate-and-fire array transceiver with address-event reconfigurable synaptic routing , 2012, 2012 IEEE Biomedical Circuits and Systems Conference (BioCAS).

[79]  Harish Bhaskaran,et al.  Integrated all-photonic non-volatile multi-level memory , 2015, Nature Photonics.

[80]  M. Pickett,et al.  A scalable neuristor built with Mott memristors. , 2013, Nature materials.

[81]  Lan Jiang,et al.  Functionalized Graphitic Carbon Nitride for Metal-free, Flexible and Rewritable Nonvolatile Memory Device via Direct Laser-Writing , 2014, Scientific Reports.

[82]  Yue Tian,et al.  Signal feature recognition based on lightwave neuromorphic signal processing. , 2011, Optics letters.

[83]  R. Stanley Williams,et al.  Direct Observation of Nanoscale Switching Centers in Metal/Molecule/Metal Structures , 2004 .

[84]  C Koos,et al.  Nonlinear silicon-on-insulator waveguides for all-optical signal processing. , 2007, Optics express.

[85]  Makoto Naruse.  Nanophotonic Information Physics: Nanointelligence and Nanophotonic Computing , 2013 .

[86]  Steven G. Johnson,et al.  A three-dimensional optical photonic crystal with designed point defects , 2004, Nature.

[87]  Behrad Gholipour,et al.  Amorphous Metal‐Sulphide Microfibers Enable Photonic Synapses for Brain‐Like Computing , 2015 .

[88]  C. Bapanayya,et al.  Simple flash evaporator for making thin films of compounds , 2010 .

[89]  Yue Tian,et al.  Photonic Neuromorphic Signal Processing and Computing , 2014 .

[90]  Din Ping Tsai,et al.  Active dielectric metasurface based on phase‐change medium , 2016 .

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

[92]  L.O. Chua,et al.  Memristive devices and systems , 1976, Proceedings of the IEEE.

[93]  Josef Humlíček,et al.  Silicon–Germanium Alloys (SixGe1-x) , 1997 .

[94]  B. Cumming,et al.  Observation of Type I Photonic Weyl Points in Optical Frequencies , 2018 .

[95]  C. David Wright,et al.  In-memory computing on a photonic platform , 2018, Science Advances.

[96]  B. Ghafary,et al.  Experimental observation of low threshold optical bistability in exfoliated graphene with low oxidation degree , 2016 .

[97]  T. Hasegawa,et al.  Short-term plasticity and long-term potentiation mimicked in single inorganic synapses. , 2011, Nature materials.

[98]  Jongkil Park,et al.  Live demonstration: Hierarchical Address-Event Routing architecture for reconfigurable large scale neuromorphic systems , 2012, 2012 IEEE International Symposium on Circuits and Systems.

[99]  Yongtian Wang,et al.  Nanometric holograms based on a topological insulator material , 2017, Nature Communications.

[100]  Richard F. Haglund,et al.  Optical nonlinearities in VO2 nanoparticles and thin films , 2004 .

[101]  V. Kravets,et al.  Engineering optical properties of a graphene oxide metamaterial assembled in microfluidic channels. , 2015, Optics express.

[102]  J. Lewis,et al.  A Germanium Inverse Woodpile Structure with a Large Photonic Band Gap , 2007 .

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

[104]  Tobi Delbrück,et al.  A 0.5V 55μW 64×2-channel binaural silicon cochlea for event-driven stereo-audio sensing , 2016, 2016 IEEE International Solid-State Circuits Conference (ISSCC).

[105]  H. M. Gibbs,et al.  Differential Gain and Bistability Using a Sodium-Filled Fabry-Perot Interferometer , 1976 .

[106]  S. Massar,et al.  Measuring the nonlinear refractive index of graphene using the optical Kerr effect method. , 2016, Optics letters.

[107]  M. Rozenberg,et al.  A Leaky‐Integrate‐and‐Fire Neuron Analog Realized with a Mott Insulator , 2017 .

[108]  N. Sharma,et al.  Effect of Te on linear and non-linear optical properties of new quaternary Ge-Se-Sb-Te chalcogenide glasses , 2014, Electronic Materials Letters.

[109]  Tobi Delbrück,et al.  Real-time, high-speed video decompression using a frame- and event-based DAVIS sensor , 2014, 2014 IEEE International Symposium on Circuits and Systems (ISCAS).

[110]  Min Gu,et al.  Highly efficient and ultra-broadband graphene oxide ultrathin lenses with three-dimensional subwavelength focusing , 2015, Nature Communications.

[111]  A. Villeneuve,et al.  Nonlinear-refractive-index measurement in As2S3 channel waveguides by asymmetric self-phase modulation , 2005 .

[112]  Rakesh K. Joshi,et al.  Chemical reduction of graphene oxide using green reductants , 2017 .

[113]  R. Stein.  A THEORETICAL ANALYSIS OF NEURONAL VARIABILITY. , 1965, Biophysical journal.

[114]  Fabien Alibart,et al.  Pattern classification by memristive crossbar circuits using ex situ and in situ training , 2013, Nature Communications.

[115]  L. Fekete,et al.  Physical properties investigation of reduced graphene oxide thin films prepared by material inkjet printing , 2017 .

[116]  Wei Zhang,et al.  Designing crystallization in phase-change materials for universal memory and neuro-inspired computing , 2019, Nature Reviews Materials.

[117]  Yue Tian,et al.  Asynchronous spiking photonic neuron for lightwave neuromorphic signal processing. , 2012, Optics letters.

[118]  Giacomo Indiveri,et al.  An event-based architecture for solving constraint satisfaction problems , 2015, Nature Communications.

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

[120]  Demetri Psaltis,et al.  Optical Neural Computers , 1987, Topical Meeting on Optical Computing.

[121]  B. Cumming,et al.  A Layered‐Composite Nanometric Sb2Te3 Material for Chiral Photonic Bandgap Engineering , 2018 .

[122]  M. Yüksek,et al.  The third order nonlinear optical characteristics of amorphous vanadium oxide thin film , 2011 .

[123]  Huug de Waardt,et al.  All fiber-optic neural network using coupled SOA based ring lasers , 2002, IEEE Trans. Neural Networks.

[124]  L. Laursen.  Wild bees: Lone rangers , 2015, Nature.

[125]  S. Mccall.  Instabilities in continuous-wave light propagation in absorbing media , 1974 .

[126]  Min Gu,et al.  Impact of Cubic symmetry on optical activity of dielectric 8-srs networks , 2018 .

[127]  Min Gu,et al.  Laser Printing of a Nano-Imager to Perform Full Optical Machine Learning , 2019, 2019 Conference on Lasers and Electro-Optics Europe & European Quantum Electronics Conference (CLEO/Europe-EQEC).

[128]  J Feldmann,et al.  Calculating with light using a chip-scale all-optical abacus , 2017, Nature Communications.

[129]  G. Indiveri,et al.  Neuromorphic architectures for spiking deep neural networks , 2015, 2015 IEEE International Electron Devices Meeting (IEDM).

[130]  B. Jia,et al.  Giant Optical Nonlinear Response of Graphene Oxide Films , 2013 .

[131]  G. L. Masson,et al.  Feedback inhibition controls spike transfer in hybrid thalamic circuits , 2002, Nature.

[132]  Fabien Alibart,et al.  Plasticity in memristive devices for spiking neural networks , 2015, Front. Neurosci..

[133]  W. Pitts,et al.  A Logical Calculus of the Ideas Immanent in Nervous Activity (1943) , 2021, Ideas That Created the Future.

[134]  Nathan Youngblood,et al.  Device‐Level Photonic Memories and Logic Applications Using Phase‐Change Materials , 2018, Advanced materials.

[135]  D. Stewart,et al.  The missing memristor found , 2008, Nature.

[136]  Simone Balatti,et al.  A 2-transistor/1-resistor artificial synapse capable of communication and stochastic learning in neuromorphic systems , 2015, Front. Neurosci..

[137]  Minghui Jiang,et al.  Multi-level coding-recoding by ultrafast phase transition on Ge2Sb2Te5 thin films , 2018, Scientific Reports.

[138]  Baohua Jia,et al.  High-photosensitive resin for super-resolution direct-laser-writing based on photoinhibited polymerization. , 2011, Optics express.

[139]  Shigeru Suzuki,et al.  VO2-dispersed glass: A new class of phase change material , 2018, Scientific Reports.

[140]  Zhen Zhou,et al.  Opportunities and challenges on nanoscale 3D neuromorphic computing system , 2017, 2017 IEEE International Symposium on Electromagnetic Compatibility & Signal/Power Integrity (EMCSI).

[141]  Calin Ciufudean,et al.  Advances in Memristor Neural Networks - Modeling and Applications , 2018 .

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