Classical Artificial Neural Network Training Using Quantum Walks as a Search Procedure

This article proposes a computational procedure that applies a quantum algorithm to train classical artificial neural networks. The goal of the procedure is to apply quantum walk as a search algorithm in a complete graph to find all synaptic weights of a classical artificial neural network. Each vertex of this complete graph represents a possible synaptic weight set in the <inline-formula><tex-math notation="LaTeX">$w$</tex-math><alternatives><mml:math><mml:mi>w</mml:mi></mml:math><inline-graphic xlink:href="desouza-ieq1-3051559.gif"/></alternatives></inline-formula>-dimensional search space, where <inline-formula><tex-math notation="LaTeX">$w$</tex-math><alternatives><mml:math><mml:mi>w</mml:mi></mml:math><inline-graphic xlink:href="desouza-ieq2-3051559.gif"/></alternatives></inline-formula> is the number of weights of the neural network. To know the number of iterations required <italic>a priori</italic> to obtain the solutions is one of the main advantages of the procedure. Another advantage is that the proposed method does not stagnate in local minimums. Thus, it is possible to use the quantum walk search procedure as an alternative to the backpropagation algorithm. The proposed method was employed for a <inline-formula><tex-math notation="LaTeX">$XOR$</tex-math><alternatives><mml:math><mml:mrow><mml:mi>X</mml:mi><mml:mi>O</mml:mi><mml:mi>R</mml:mi></mml:mrow></mml:math><inline-graphic xlink:href="desouza-ieq3-3051559.gif"/></alternatives></inline-formula> problem to prove the proposed concept. To solve this problem, the proposed method trained a classical artificial neural network with nine weights. However, the procedure can find solutions for any number of dimensions. The results achieved demonstrate the viability of the proposal, contributing to machine learning and quantum computing researches.

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

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

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

[4]  Ignacio Rojas,et al.  Neural networks: An overview of early research, current frameworks and new challenges , 2016, Neurocomputing.

[5]  Hans-J. Briegel,et al.  Quantum-enhanced machine learning , 2016, Physical review letters.

[6]  Mohit Singh,et al.  Evolution in Quantum Computing , 2016, 2016 International Conference System Modeling & Advancement in Research Trends (SMART).

[7]  Neil B. Lovett,et al.  The quantum walk search algorithm: factors affecting efficiency , 2011, Mathematical Structures in Computer Science.

[8]  Salvador Elías Venegas-Andraca,et al.  Quantum walks: a comprehensive review , 2012, Quantum Information Processing.

[9]  Václav Snásel,et al.  Metaheuristic design of feedforward neural networks: A review of two decades of research , 2017, Eng. Appl. Artif. Intell..

[10]  Thomas G. Wong,et al.  Grover search with lackadaisical quantum walks , 2015, 1502.04567.

[11]  Gilles Brassard,et al.  Tight bounds on quantum searching , 1996, quant-ph/9605034.

[12]  Nikolajs Nahimovs,et al.  Exceptional Configurations of Quantum Walks with Grover's Coin , 2015, MEMICS.

[13]  Ashish Kapoor,et al.  Quantum Perceptron Models , 2016, NIPS.

[14]  Ivan Nunes da Silva,et al.  Artificial Neural Networks: A Practical Course , 2016 .

[15]  Thierry Paul,et al.  Quantum computation and quantum information , 2007, Mathematical Structures in Computer Science.

[16]  R. Wu,et al.  Quantum Circuit Design for Training Perceptron Models , 2018, 1802.05428.

[17]  Gilles Brassard,et al.  Machine Learning in a Quantum World , 2006, Canadian AI.

[18]  Thomas G. Wong,et al.  Faster search by lackadaisical quantum walk , 2017, Quantum Information Processing.

[19]  K. Birgitta Whaley,et al.  Quantum random-walk search algorithm , 2002, quant-ph/0210064.

[20]  Tiago Ferreira,et al.  Quantum Walk to Train a Classical Artificial Neural Network , 2019, 2019 8th Brazilian Conference on Intelligent Systems (BRACIS).

[21]  S. Lloyd,et al.  Quantum algorithms for supervised and unsupervised machine learning , 2013, 1307.0411.

[22]  Nikolajs Nahimovs.  Lackadaisical Quantum Walks with Multiple Marked Vertices , 2019, SOFSEM.

[23]  J. R. Powell.  The Quantum Limit to Moore's Law , 2008 .

[24]  Catherine D. Schuman,et al.  A Classical-Quantum Hybrid Approach for Unsupervised Probabilistic Machine Learning , 2019, Lecture Notes in Networks and Systems.

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

[26]  Peter Wittek,et al.  Quantum Machine Learning: What Quantum Computing Means to Data Mining , 2014 .

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

[28]  Yuan Feng,et al.  Proof rules for the correctness of quantum programs , 2007, Theor. Comput. Sci..

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

[30]  R. Portugal.  Quantum Walks and Search Algorithms , 2013 .