Implementation of quantum stochastic walks for function approximation, two-dimensional data classification, and sequence classification

Abstract

We study a quantum stochastic neural network (QSNN) based on quantum stochastic walks on a graph, and use gradient descent to update the network parameters. We apply a toy model of QSNN with a few neurons to the problems of function approximation, two-dimensional data classification, and sequence classification. A simple QSNN with five neurons is trained to determine whether a sequence of words is a sentence or not, and we find that a QSNN can reduce the number of training steps. A QSNN with 11 neurons shows a quantum advantage in improving the accuracy of recognizing new types of inputs like verses. Moreover, with our toy model, we find the coherent QSNN is more robust against both label noise and device noise, compared with the decoherent QSNN. These results show that quantum stochastic walks may be a useful resource to implement a quantum neural network.

arXiv comment17 pages, 14 figures

References in corpus (39)

• Supplementary information for "Quantum supremacy using a programmable superconducting processor"
• Quantum Machine Learning
• Quantum Mechanics helps in searching for a needle in a haystack
• Quantum Computing
• Quantum algorithm for solving linear systems of equations
• Quantum computational advantage using photons
• Barren plateaus in quantum neural network training landscapes
• Solving the Quantum Many-Body Problem with Artificial Neural Networks
• Quantum Circuit Learning
• Quantum Convolutional Neural Networks
• Quantum algorithms: an overview
• Efficient Learning for Deep Quantum Neural Networks
• Quantum advantage in learning from experiments
• Realization of quantum walks with negligible decoherence in waveguide lattices
• Quantum generative adversarial networks
• Continuous-variable quantum neural networks
• Quantum Boltzmann Machine
• Efficient Representation of Quantum Many-body States with Deep Neural Networks
• Hierarchical quantum classifiers
• Quantum generalisation of feedforward neural networks
• An Artificial Neuron Implemented on an Actual Quantum Processor
• Information-theoretic bounds on quantum advantage in machine learning
• Experimental Implementation of the Quantum Random-Walk Algorithm
• Experimental Two-dimensional Quantum Walk on a Photonic Chip
• Provably efficient machine learning for quantum many-body problems
• Quantum Hopfield neural network
• Quantum generative adversarial network for generating discrete distribution
• Quantum stochastic walks: A generalization of classical random walks and quantum walks
• Quantum autoencoders to denoise quantum data
• Quantum perceptron over a field and neural network architecture selection in a quantum computer
• Learning and Inference on Generative Adversarial Quantum Circuits
• On the Computational Efficiency of Training Neural Networks
• Building quantum neural networks based on swap test
• Quantum walks on graphs representing the firing patterns of a quantum neural network
• Variational quantum compiling with double Q-learning
• Experimental quantum stochastic walks simulating associative memory of Hopfield neural networks
• Probability density of quantum expectation values
• Quantum State Discrimination on Reconfigurable Noise-Robust Quantum Networks
• Experimental multi-state quantum discrimination through a Quantum network

Cited by in corpus (6)

• Review on Quantum Walk Computing: Theory, Implementation, and Application
• Quantum support vector machines for aerodynamic classification
• Efficient learning of mixed-state tomography for photonic quantum walk
• Hybrid Quantum-inspired Resnet and Densenet for Pattern Recognition
• Recurrence in discrete-time quantum stochastic walks
• Quantum Sparse Coding and Decoding Based on Quantum Network