Continuous-variable deep quantum neural networks for flexible learning of structured classical information

DOI10.4208/CICP.OA-2020-0173MaRDI QIDQ5163883zbMATH OpenOpenAlexFDO

Authors Jasvith Raj Basani, Aranya B. Bhattacherjee

Publication date 9 November 2021

Published in Communications in Computational Physics (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/2006.10927

zbMATH Keywords

continuous variable modelquantum computingquantum optics

Mathematics Subject Classification ID

Artificial neural networks and deep learning (68T07) Quantum information, communication, networks (quantum-theoretic aspects) (81P45) Quantum computation (81P68)

Abstract: Quantum computation using optical modes has been well-established in its ability to construct deep neural networks. These networks have been shown to be flexible both architecturally as well as in terms of the type of data being processed. We leverage this property of the Continuous-Variable (CV) model to construct stacked single mode networks that are shown to learn structured classical information, while placing no restrictions on the size of the network, and at the same time maintaining it's complexity. The hallmark of the CV model is its ability to forge non-linear functions using a set of gates that allows it to remain completely unitary. The proposed model exemplifies that the appropriate photonic hardware can be integrated with present day optical communication systems to meet our information processing requirements. In this paper, using the Strawberry Fields software library on the MNIST dataset of hand-written digits, we demonstrate the adaptability of the network to learn classical information to fidelities of greater than 99.98%

Recommendations

• Continuous variable quantum perceptron
• Quantum enhanced cross-validation for near-optimal neural networks architecture selection
• A quantum model of feed-forward neural networks with unitary learning algorithms
• A hybrid quantum-classical neural network with deep residual learning
• Variational convolutional neural networks classifiers

Cites work

• Central limit theorems for Gaussian polytopes
• Deep learning

Cited in

(8)

• A conditional generative model based on quantum circuit and classical optimization
• Explicit demonstration of initial state construction in artificial neural networks using netket and IBM Q experience platform
• Continuous variable quantum perceptron
• Quantum Implementation of Numerical Methods for Convection-Diffusion Equations: Toward Computational Fluid Dynamics
• Quantum machine learning based on continuous variable single-photon states: an elementary foundation for quantum neural networks
• Domain adaptation based on hybrid classical-quantum neural network
• Efficient quantum feature extraction for CNN-based learning
• Quantum continual learning of quantum data realizing knowledge backward transfer

Describes a project that uses

Uses Software

• MNIST
• TensorFlow
• Strawberry Fields
• Adam

This page was built for publication: Continuous-variable deep quantum neural networks for flexible learning of structured classical information

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5163883)