Spoken Digit Classification by In-Materio Reservoir Computing With Neuromorphic Atomic Switch Networks

Atomic Switch Networks comprising silver iodide (AgI) junctions, a material previously unexplored as functional memristive elements within highly interconnected nanowire networks, were employed as a neuromorphic substrate for physical Reservoir Computing This new class of ASN-based devices has been physically characterized and utilized to classify spoken digit audio data, demonstrating the utility of substrate-based device architectures where intrinsic material properties can be exploited to perform computation in-materio. This work demonstrates high accuracy in the classification of temporally analyzed Free-Spoken Digit Data These results expand upon the class of viable memristive materials available for the production of functional nanowire networks and bolster the utility of ASN-based devices as unique hardware platforms for neuromorphic computing applications involving memory, adaptation and learning.

[1]  Julian F. Miller,et al.  Reservoir Computing as a Model for In-Materio Computing , 2017 .

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

[3]  Mikko H. Lipasti,et al.  Automatic abstraction and fault tolerance in cortical microachitectures , 2011, 2011 38th Annual International Symposium on Computer Architecture (ISCA).

[4]  Kohei Nakajima,et al.  Physical reservoir computing—an introductory perspective , 2020, Japanese Journal of Applied Physics.

[5]  Alireza Goudarzi,et al.  Reservoir Computing Approach to Robust Computation Using Unreliable Nanoscale Networks , 2014, UCNC.

[6]  Shimeng Yu,et al.  Low-Energy Robust Neuromorphic Computation Using Synaptic Devices , 2012, IEEE Transactions on Electron Devices.

[7]  C. Sunandana,et al.  Optical absorption and Photoluminescence in ultra thin silver and silver iodide films , 2008, 2008 IEEE PhotonicsGlobal@Singapore.

[8]  Z. Zolnai,et al.  Nanosecond resistive switching in Ag/AgI/PtIr nanojunctions , 2020, Beilstein journal of nanotechnology.

[9]  Susan Stepney,et al.  Reservoir Computing with Computational Matter , 2018 .

[10]  James Gimzewski,et al.  Reservoir Computing with Neuromemristive Nanowire Networks , 2020, 2020 International Joint Conference on Neural Networks (IJCNN).

[11]  Christof Teuscher,et al.  The Weird, the Small, and the Uncontrollable: Redefining the Frontiers of Computing , 2017, Computer.

[12]  Toshiyuki Yamane,et al.  Recent Advances in Physical Reservoir Computing: A Review , 2018, Neural Networks.

[13]  A. Stieg,et al.  Harnessing adaptive dynamics in neuro-memristive nanowire networks for transfer learning , 2020, 2020 International Conference on Rebooting Computing (ICRC).

[14]  Akshay Madhav Deshmukh.  Comparison of Hidden Markov Model and Recurrent Neural Network in Automatic Speech Recognition , 2020, European Journal of Engineering Research and Science.

[15]  Omid Kavehei,et al.  Neuromorphic Information Processing with Nanowire Networks , 2020, 2020 IEEE International Symposium on Circuits and Systems (ISCAS).

[16]  Konstantin K. Likharev,et al.  Neuromorphic architectures for nanoelectronic circuits , 2004, Int. J. Circuit Theory Appl..

[17]  Benjamin Schrauwen,et al.  An overview of reservoir computing: theory, applications and implementations , 2007, ESANN.

[18]  E. D’Angelo.  The human brain project. , 2012, Functional neurology.

[19]  C. Sunandana,et al.  Surface plasmon–exciton transition in ultra-thin silver and silver iodide films , 2007 .

[20]  Christof Teuscher,et al.  Computational Capabilities of Random Automata Networks for Reservoir Computing , 2012, Physical review. E, Statistical, nonlinear, and soft matter physics.

[21]  Seung Hwan Lee,et al.  Reservoir computing using dynamic memristors for temporal information processing , 2017, Nature Communications.

[22]  Mantas Lukosevicius,et al.  Reservoir Computing and Self-Organized Neural Hierarchies , 2012 .

[23]  Narayan Srinivasa,et al.  Neuromorphic Adaptive Plastic Scalable Electronics: Analog Learning Systems , 2012, IEEE Pulse.

[24]  Julian Francis Miller,et al.  Evolution in Materio , 2009, Encyclopedia of Complexity and Systems Science.

[25]  Seung Hwan Lee,et al.  Temporal data classification and forecasting using a memristor-based reservoir computing system , 2019, Nature Electronics.

[26]  Jens Bürger,et al.  Computational Capacity and Energy Consumption of Complex Resistive Switch Networks , 2015, ArXiv.

[27]  Tetsuya Asai,et al.  Simple Reservoir Computing Capitalizing on the Nonlinear Response of Materials: Theory and Physical Implementations , 2021, Physical Review Applied.

[28]  민범기.  Surface Plasmon 기술 , 2009 .

[29]  Qiangfei Xia,et al.  Reservoir Computing Using Diffusive Memristors , 2019, Adv. Intell. Syst..

[30]  Benjamin J Wiley,et al.  Emergence of winner-takes-all connectivity paths in random nanowire networks , 2018, Nature Communications.

[31]  J Joshua Yang,et al.  Memristive devices for computing. , 2013, Nature nanotechnology.

[32]  Thomas Schatz,et al.  Neural network vs. HMM speech recognition systems as models of human cross-linguistic phonetic perception , 2018 .

[33]  Bo Li,et al.  Hysteretic Current-Voltage Characteristics and Memristive Behaviors in AgI Nano-Particles Assembly , 2013 .

[34]  Takuro Tamura,et al.  Rate-Limiting Processes Determining the Switching Time in a Ag2S Atomic Switch , 2010 .

[35]  Benjamin Schrauwen,et al.  Reservoir Computing Trends , 2012, KI - Künstliche Intelligenz.

[36]  S. Menzel,et al.  Understanding the switching-off mechanism in Ag+ migration based resistively switching model systems , 2007 .

[37]  X. Liang,et al.  Resistive switching and memory effects of AgI thin film , 2007 .

[38]  Enrico Macii,et al.  The Human Brain Project and neuromorphic computing. , 2013, Functional neurology.

[39]  Shenghao Wang,et al.  Silver Iodide Formation in Methyl Ammonium Lead Iodide Perovskite Solar Cells with Silver Top Electrodes , 2015 .

[40]  Masakazu Aono,et al.  Nanoarchitectonic atomic switch networks for unconventional computing , 2016 .

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

[42]  Yuchao Yang,et al.  Observation of conducting filament growth in nanoscale resistive memories , 2012, Nature Communications.

[43]  Kofi Appiah,et al.  A comparative review of dynamic neural networks and hidden Markov model methods for mobile on-device speech recognition , 2017, Neural Computing and Applications.

[44]  Herbert Jaeger,et al.  Reservoir computing approaches to recurrent neural network training , 2009, Comput. Sci. Rev..

[45]  Christof Teuscher,et al.  Non-temporal logic performance of an atomic switch network , 2017, 2017 IEEE/ACM International Symposium on Nanoscale Architectures (NANOARCH).

[46]  Abdul Sattar,et al.  Quantized conductance and switching in percolating nanoparticle films. , 2013, Physical review letters.

[47]  Justin D. Holmes,et al.  Nonpolar Resistive Switching in Ag@TiO2 Core-Shell Nanowires. , 2017, ACS applied materials & interfaces.

[48]  Huaqiang Wu,et al.  Dynamic memristor-based reservoir computing for high-efficiency temporal signal processing , 2021, Nature Communications.

[49]  Masakazu Aono,et al.  A theoretical and experimental study of neuromorphic atomic switch networks for reservoir computing , 2013, Nanotechnology.

[50]  Benjamin Schrauwen,et al.  Photonic reservoir computing: A new approach to optical information processing , 2010, 2010 12th International Conference on Transparent Optical Networks.

[51]  T. Hasegawa,et al.  Learning Abilities Achieved by a Single Solid‐State Atomic Switch , 2010, Advanced materials.

[52]  C Joachim,et al.  Direct determination of the energy required to operate a single molecule switch. , 2003, Physical review letters.

[53]  Julian Francis Miller,et al.  Evolution-in-materio: evolving computation in materials , 2014, Evolutionary Intelligence.

[54]  K. Terabe,et al.  Quantized conductance atomic switch , 2005, Nature.

[55]  Masakazu Aono,et al.  Self-organized atomic switch networks , 2013 .

[56]  Julian Francis Miller,et al.  Evolution in materio: looking beyond the silicon box , 2002, Proceedings 2002 NASA/DoD Conference on Evolvable Hardware.

[57]  Adam Z. Stieg,et al.  Neuromorphic Atomic Switch Networks , 2012, PloS one.

[58]  R. Waser,et al.  Quantum conductance and switching kinetics of AgI-based microcrossbar cells , 2012, Nanotechnology.

[59]  Cory Merkel,et al.  Design and Analysis of a Neuromemristive Reservoir Computing Architecture for Biosignal Processing , 2016, Front. Neurosci..

[60]  Benjamin Schrauwen,et al.  The Introduction of Time-Scales in Reservoir Computing, Applied to Isolated Digits Recognition , 2007, ICANN.

[61]  He Qian,et al.  Understanding memristive switching via in situ characterization and device modeling , 2019, Nature Communications.