Opportunities in Quantum Reservoir Computing and Extreme Learning Machines

Quantum reservoir computing (QRC) and quantum extreme learning machines (QELM) are two emerging approaches that have demonstrated their potential both in classical and quantum machine learning tasks. They exploit the quantumness of physical systems combined with an easy training strategy, achieving an excellent performance. The increasing interest in these unconventional computing approaches is fueled by the availability of diverse quantum platforms suitable for implementation and the theoretical progresses in the study of complex quantum systems. In this perspective article, we overview recent proposals and first experiments displaying a broad range of possibilities when quantum inputs, quantum physical substrates and quantum tasks are considered. The main focus is the performance of these approaches, on the advantages with respect to classical counterparts and opportunities.

[1]  Amir F. Atiya,et al.  New results on recurrent network training: unifying the algorithms and accelerating convergence , 2000, IEEE Trans. Neural Networks Learn. Syst..

[2]  A. Kutvonen,et al.  Optimizing a quantum reservoir computer for time series prediction , 2018, Scientific Reports.

[3]  Damien Rontani,et al.  Human action recognition with a large-scale brain-inspired photonic computer , 2019, Nat. Mach. Intell..

[4]  Henry Markram,et al.  Real-Time Computing Without Stable States: A New Framework for Neural Computation Based on Perturbations , 2002, Neural Computation.

[5]  Miguel C. Soriano,et al.  Gaussian states of continuous-variable quantum systems provide universal and versatile reservoir computing , 2021, Communications Physics.

[6]  Dianhui Wang,et al.  Extreme learning machines: a survey , 2011, Int. J. Mach. Learn. Cybern..

[7]  Juan-Pablo Ortega,et al.  Echo state networks are universal , 2018, Neural Networks.

[8]  R. Nichols,et al.  A hybrid machine learning algorithm for designing quantum experiments , 2018, Quantum Machine Intelligence.

[9]  Andrzej Opala,et al.  Quantum reservoir processing , 2018, npj Quantum Information.

[10]  B. Schrauwen,et al.  Reservoir computing and extreme learning machines for non-linear time-series data analysis , 2013, Neural Networks.

[11]  Rodrigo Alvarez-Icaza,et al.  Neurogrid: A Mixed-Analog-Digital Multichip System for Large-Scale Neural Simulations , 2014, Proceedings of the IEEE.

[12]  Giacomo Indiveri,et al.  Memory and Information Processing in Neuromorphic Systems , 2015, Proceedings of the IEEE.

[13]  Keisuke Fujii,et al.  Boosting Computational Power through Spatial Multiplexing in Quantum Reservoir Computing , 2018, Physical Review Applied.

[14]  Andrew S. Cassidy,et al.  Convolutional networks for fast, energy-efficient neuromorphic computing , 2016, Proceedings of the National Academy of Sciences.

[15]  Nicolas Treps,et al.  Reconfigurable optical implementation of quantum complex networks , 2017, 1708.08726.

[16]  M. C. Soriano,et al.  A Unified Framework for Reservoir Computing and Extreme Learning Machines based on a Single Time-delayed Neuron , 2015, Scientific Reports.

[17]  Tomasz Paterek,et al.  Creating and concentrating quantum resource states in noisy environments using a quantum neural network , 2021, Neural Networks.

[18]  M S Allman,et al.  Demonstration of the trapped-ion quantum CCD computer architecture. , 2021, Nature.

[19]  Tomasz Paterek,et al.  Quantum Neuromorphic Platform for Quantum State Preparation. , 2019, Physical review letters.

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

[21]  Jacob biamonte,et al.  Quantum machine learning , 2016, Nature.

[22]  Harald Haas,et al.  Harnessing Nonlinearity: Predicting Chaotic Systems and Saving Energy in Wireless Communication , 2004, Science.

[23]  L. C. G. Govia,et al.  Quantum reservoir computing with a single nonlinear oscillator , 2020, Physical Review Research.

[24]  Maria Schuld,et al.  The quest for a Quantum Neural Network , 2014, Quantum Information Processing.

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

[26]  Zoran Konkoli,et al.  On Reservoir Computing: From Mathematical Foundations to Unconventional Applications , 2017 .

[27]  Rita Toth,et al.  Advances in unconventional computing , 2017 .

[28]  Hans-J. Briegel,et al.  Machine learning \& artificial intelligence in the quantum domain , 2017, ArXiv.

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

[30]  Maria Schuld,et al.  Quantum Machine Learning in Feature Hilbert Spaces. , 2018, Physical review letters.

[31]  George C. Valley,et al.  Classification of time-domain waveforms using a speckle-based optical reservoir computer. , 2020, Optics express.

[32]  Lu-Ming Duan,et al.  Machine learning meets quantum physics , 2019, Physics Today.

[33]  Naftali Tishby,et al.  Machine learning and the physical sciences , 2019, Reviews of Modern Physics.

[34]  H. Nurdin,et al.  Temporal Information Processing on Noisy Quantum Computers , 2020, Physical Review Applied.

[35]  Stefan Lessmann,et al.  Extreme learning machines for credit scoring: An empirical evaluation , 2017, Expert Syst. Appl..

[36]  Simone Severini,et al.  Quantum machine learning: a classical perspective , 2017, Proceedings of the Royal Society A: Mathematical, Physical and Engineering Sciences.

[37]  Miss A.O. Penney.  (b) , 1974, The New Yale Book of Quotations.

[38]  Steve B. Furber,et al.  The SpiNNaker Project , 2014, Proceedings of the IEEE.

[39]  Miguel C. Soriano,et al.  Reservoir computing with a single time-delay autonomous Boolean node , 2014, Physical review. E, Statistical, nonlinear, and soft matter physics.

[40]  Jaideep Pathak,et al.  Model-Free Prediction of Large Spatiotemporally Chaotic Systems from Data: A Reservoir Computing Approach. , 2018, Physical review letters.

[41]  Giulia Marcucci,et al.  Theory of neuromorphic computing by waves: machine learning by rogue waves, dispersive shocks, and solitons , 2019, Physical review letters.

[42]  Stefano Mancini,et al.  Continuous Variable Quantum Perceptron. , 2019 .

[43]  Y. Cai,et al.  Multimode entanglement in reconfigurable graph states using optical frequency combs , 2017, Nature Communications.

[44]  C. Wright,et al.  Beyond von‐Neumann Computing with Nanoscale Phase‐Change Memory Devices , 2013 .

[45]  Chee Kheong Siew,et al.  Extreme learning machine: Theory and applications , 2006, Neurocomputing.

[46]  Julie Grollier,et al.  Quantum neuromorphic computing , 2020 .

[47]  J. van Leeuwen,et al.  Neural Networks: Tricks of the Trade , 2002, Lecture Notes in Computer Science.

[48]  Hanwu Chen,et al.  Cryptanalysis and improvement in controlled quantum dialogue using cluster states , 2019, Quantum Information Processing.

[49]  Alicia J. Kollár,et al.  Hyperbolic lattices in circuit quantum electrodynamics , 2018, Nature.

[50]  S. Pirandola,et al.  Entanglement classification via neural network quantum states , 2019, New Journal of Physics.

[51]  Tsuyoshi Murata,et al.  {m , 1934, ACML.

[52]  K. Aberer,et al.  German National Research Center for Information Technology , 2007 .

[53]  Don Monroe,et al.  A new type of mathematics? , 2014, CACM.

[54]  M. C. Soriano,et al.  Information Processing Capacity of Spin-Based Quantum Reservoir Computing Systems , 2020, Cognitive Computation.

[55]  Yuya O. Nakagawa,et al.  Predicting excited states from ground state wavefunction by supervised quantum machine learning , 2020, Mach. Learn. Sci. Technol..

[56]  Kristan Temme,et al.  Supervised learning with quantum-enhanced feature spaces , 2018, Nature.

[57]  Elizabeth C. Behrman,et al.  Simulations of quantum neural networks , 2000, Inf. Sci..

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

[59]  Mantas Lukosevicius,et al.  A Practical Guide to Applying Echo State Networks , 2012, Neural Networks: Tricks of the Trade.

[60]  Seth Lloyd,et al.  Continuous-variable quantum neural networks , 2018, Physical Review Research.

[61]  Gilles Brassard,et al.  Quantum speed-up for unsupervised learning , 2012, Machine Learning.

[62]  Guang-Bin Huang,et al.  Trends in extreme learning machines: A review , 2015, Neural Networks.

[63]  Benjamin Schrauwen,et al.  Information Processing Capacity of Dynamical Systems , 2012, Scientific Reports.

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

[65]  Giacomo Indiveri,et al.  Integration of nanoscale memristor synapses in neuromorphic computing architectures , 2013, Nanotechnology.

[66]  Jonathan C. F. Matthews,et al.  Designing quantum experiments with a genetic algorithm , 2018, ArXiv.

[67]  Marek Wegrzyn,et al.  Hardware implementation of real-time Extreme Learning Machine in FPGA: Analysis of precision, resource occupation and performance , 2016, Comput. Electr. Eng..

[68]  Andrzej Opala,et al.  Reconstructing Quantum States With Quantum Reservoir Networks , 2020, IEEE Transactions on Neural Networks and Learning Systems.

[69]  Keisuke Fujii,et al.  Harnessing disordered quantum dynamics for machine learning , 2016, 1602.08159.

[70]  Giovanni Acampora,et al.  Quantum machine intelligence , 2019, Quantum Mach. Intell..