Quantum superposition inspired spiking neural network

Summary Despite advances in artificial intelligence models, neural networks still cannot achieve human performance, partly due to differences in how information is encoded and processed compared with human brain. Information in an artificial neural network (ANN) is represented using a statistical method and processed as a fitting function, enabling handling of structural patterns in image, text, and speech processing. However, substantial changes to the statistical characteristics of the data, for example, reversing the background of an image, dramatically reduce the performance. Here, we propose a quantum superposition spiking neural network (QS-SNN) inspired by quantum mechanisms and phenomena in the brain, which can handle reversal of image background color. The QS-SNN incorporates quantum theory with brain-inspired spiking neural network models from a computational perspective, resulting in more robust performance compared with traditional ANN models, especially when processing noisy inputs. The results presented here will inform future efforts to develop brain-inspired artificial intelligence.

[1]  S. S. Iyengar,et al.  Analysis of Five Techniques for the Internal Representation of a Digital Image Inside a Quantum Processor , 2020, SN Computer Science.

[2]  L. Abbott,et al.  Competitive Hebbian learning through spike-timing-dependent synaptic plasticity , 2000, Nature Neuroscience.

[3]  A. Moustafa,et al.  The effects of dynamical synapses on firing rate activity: a spiking neural network model , 2017, The European journal of neuroscience.

[4]  Matthew P. A. Fisher,et al.  Quantum Cognition: The possibility of processing with nuclear spins in the brain , 2015, 1508.05929.

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

[6]  Garrick Orchard,et al.  SLAYER: Spike Layer Error Reassignment in Time , 2018, NeurIPS.

[7]  W. Gerstner,et al.  Chapter 12 A framework for spiking neuron models: The spike response model , 2001 .

[8]  Alán Aspuru-Guzik,et al.  An artificial spiking quantum neuron , 2019, npj Quantum Information.

[9]  Yoshua Bengio,et al.  Gradient-based learning applied to document recognition , 1998, Proc. IEEE.

[10]  Y. Dan,et al.  Spike Timing-Dependent Plasticity of Neural Circuits , 2004, Neuron.

[11]  Khoa Luu,et al.  Image Processing in Quantum Computers , 2018, ArXiv.

[12]  Ilana B. Witten,et al.  Striatal circuits for reward learning and decision-making , 2019, Nature Reviews Neuroscience.

[13]  E. Torrontegui,et al.  Unitary quantum perceptron as efficient universal approximator , 2018, EPL (Europhysics Letters).

[14]  T. Boraud,et al.  Decision making under uncertainty in a spiking neural network model of the basal ganglia. , 2016, Journal of integrative neuroscience.

[15]  Andrew Zisserman,et al.  Very Deep Convolutional Networks for Large-Scale Image Recognition , 2014, ICLR.

[16]  A. Harrow,et al.  Quantum algorithm for linear systems of equations. , 2008, Physical review letters.

[17]  Yong Tang,et al.  A quantum-inspired genetic algorithm for k-means clustering , 2010, Expert Syst. Appl..

[18]  M. B. Plenio,et al.  Quantum coherence in ion channels: resonances, transport and verification , 2010, 1006.3892.

[19]  Yi Zeng,et al.  Towards a Brain-Inspired Developmental Neural Network by Adaptive Synaptic Pruning , 2017, ICONIP.

[20]  Jian Sun,et al.  Deep Residual Learning for Image Recognition , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[21]  Wulfram Gerstner,et al.  SPIKING NEURON MODELS Single Neurons , Populations , Plasticity , 2002 .

[22]  Alán Aspuru-Guzik,et al.  Quantum Neuron: an elementary building block for machine learning on quantum computers , 2017, ArXiv.

[23]  Maria Schuld,et al.  Simulating a perceptron on a quantum computer , 2014, ArXiv.

[24]  Wofgang Maas,et al.  Networks of spiking neurons: the third generation of neural network models , 1997 .

[25]  Madhav J. Nigam,et al.  Applications of quantum inspired computational intelligence: a survey , 2014, Artificial Intelligence Review.

[26]  W. Senn,et al.  Learning by the Dendritic Prediction of Somatic Spiking , 2014, Neuron.

[27]  Mario Mastriani,et al.  Quantum Image Processing: the truth, the whole truth, and nothing but the truth about its problems on internal image representation and outcomes recovering , 2020, 2002.04394.

[28]  Eugene M. Izhikevich,et al.  Simple model of spiking neurons , 2003, IEEE Trans. Neural Networks.

[29]  Kaoru Hirota,et al.  A flexible representation of quantum images for polynomial preparation, image compression, and processing operations , 2011, Quantum Inf. Process..

[30]  Roland Vollgraf,et al.  Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms , 2017, ArXiv.

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

[32]  S. Lloyd,et al.  Quantum principal component analysis , 2013, Nature Physics.

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

[34]  Everton J. Agnes,et al.  Diverse synaptic plasticity mechanisms orchestrated to form and retrieve memories in spiking neural networks , 2015, Nature Communications.

[35]  Kilian Q. Weinberger,et al.  Densely Connected Convolutional Networks , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[36]  Peter W. Shor.  Polynomial-Time Algorithms for Prime Factorization and Discrete Logarithms on a Quantum Computer , 1999 .

[37]  Yi Zeng,et al.  Improving multi-layer spiking neural networks by incorporating brain-inspired rules , 2017, Science China Information Sciences.

[38]  Hiroshi Tsujino,et al.  The neural mechanism for the initiation timing of both self-timed actions and simple reactions: a spiking network model of the basal ganglia. , 2010, Neuroscience Research.

[39]  P. Doraiswamy,et al.  A New Spin on Neural Processing: Quantum Cognition , 2016, Front. Hum. Neurosci..

[40]  W. Gerstner,et al.  Neuromodulated Spike-Timing-Dependent Plasticity, and Theory of Three-Factor Learning Rules , 2016, Front. Neural Circuits.