Accelerating spiking neural networks using quantum algorithm with high success probability and high calculation accuracy

Utilizing quantum computers to deploy artificial neural networks (ANNs) will bring the potential of significant advancements in both speed and scale. In this paper, we propose a kind of quantum spike neural networks (SNNs) as well as comprehensively evaluate and give a detailed mathematical proof for the quantum SNNs, including its successful probability, calculation accuracy, and algorithm complexity. The proof shows the quantum SNNs' computational complexity that is log-polynomial in the data dimension. Furthermore, we provide a method to improve quantum SNNs' minimum successful probability to nearly 100%. Finally, we present the good performance of quantum SNNs for solving pattern recognition from the real-world.

[1]  Ievgeniia Oshurko.  Quantum Machine Learning , 2020, Quantum Computing.

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

[3]  G. Brassard,et al.  Quantum Amplitude Amplification and Estimation , 2000, quant-ph/0005055.

[4]  Lov K. Grover,et al.  Synthesis of quantum superpositions by quantum computation , 2000, Physical review letters.

[5]  Chiara Macchiavello,et al.  An artificial neuron implemented on an actual quantum processor , 2018, npj Quantum Information.

[6]  Gerard J. Milburn.  An introduction to quantum computing , 2007, Quantum Inf. Comput..

[7]  K. Edee,et al.  ADVANCES IN IMAGING AND ELECTRON PHYSICS , 2016 .

[8]  Lov K. Grover.  A fast quantum mechanical algorithm for database search , 1996, STOC '96.

[9]  S. Lloyd,et al.  Quantum Hopfield neural network , 2017, Physical Review A.

[10]  Filip Ponulak,et al.  Introduction to spiking neural networks: Information processing, learning and applications. , 2011, Acta neurobiologiae experimentalis.

[11]  Soonwon Choi,et al.  Quantum convolutional neural networks , 2018, Nature Physics.

[12]  D. Berry,et al.  Black-Box Quantum State Preparation without Arithmetic. , 2018, Physical review letters.

[13]  Marcello Benedetti,et al.  Parameterized quantum circuits as machine learning models , 2019, Quantum Science and Technology.

[14]  Lov K. Grover,et al.  Creating superpositions that correspond to efficiently integrable probability distributions , 2002, quant-ph/0208112.

[15]  Kaushik Roy,et al.  Towards spike-based machine intelligence with neuromorphic computing , 2019, Nature.

[16]  Joel Zylberberg,et al.  Inhibitory Interneurons Decorrelate Excitatory Cells to Drive Sparse Code Formation in a Spiking Model of V1 , 2013, The Journal of Neuroscience.

[17]  Ajit Narayanan,et al.  Quantum artificial neural network architectures and components , 2000, Inf. Sci..

[18]  Raymond Laflamme,et al.  An Introduction to Quantum Computing , 2007, Quantum Inf. Comput..

[19]  Sergios Theodoridis,et al.  Neural Networks and Deep Learning , 2015 .

[20]  Nathan Killoran,et al.  Quantum generative adversarial networks , 2018, Physical Review A.

[21]  Charles H. Bennett,et al.  Notes on Landauer's Principle, Reversible Computation, and Maxwell's Demon , 2002, physics/0210005.

[22]  Isaac L. Chuang,et al.  Quantum Computation and Quantum Information (10th Anniversary edition) , 2011 .

[23]  M. Razavy,et al.  Quantum Theory of Tunneling (2nd Edition) , 2013 .

[24]  Tobias J. Osborne,et al.  Training deep quantum neural networks , 2020, Nature Communications.

[25]  Nobuyuki Matsui,et al.  Qubit neural network and its learning efficiency , 2005, Neural Computing & Applications.

[26]  Geoffrey E. Hinton,et al.  Deep Learning , 2015, Nature.

[27]  R. Cleve,et al.  Quantum fingerprinting. , 2001, Physical review letters.

[28]  Kay Chen Tan,et al.  Pattern recognition computation in a spiking neural network with temporal encoding and learning , 2012, The 2012 International Joint Conference on Neural Networks (IJCNN).

[29]  Ivano Tavernelli,et al.  Quantum implementation of an artificial feed-forward neural network , 2019 .

[30]  Edoardo Charbon,et al.  From the Quantum Moore's Law toward Silicon Based Universal Quantum Computing , 2017, 2017 IEEE International Conference on Rebooting Computing (ICRC).

[31]  Arvid J. Bessen.  Lower bound for quantum phase estimation , 2005 .

[32]  J. Stein,et al.  Auditory temporal coding in dyslexia , 1996, Proceedings of the Royal Society of London. Series B: Biological Sciences.

[33]  Yutaro Iiyama.  Quantum state preparation with multiplicative amplitude transduction , 2020 .

[34]  H. Sompolinsky,et al.  The tempotron: a neuron that learns spike timing–based decisions , 2006, Nature Neuroscience.

[35]  Lov K. Grover.  Quantum Mechanics Helps in Searching for a Needle in a Haystack , 1997, quant-ph/9706033.

[36]  Alán Aspuru-Guzik,et al.  Quantum autoencoders for efficient compression of quantum data , 2016, 1612.02806.

[37]  Stefan Woerner,et al.  Quantum Generative Adversarial Networks for learning and loading random distributions , 2019, npj Quantum Information.