Continuous variable quantum perceptron

DOI10.1142/S0219749919410090MaRDI QIDQ5219353zbMATH OpenFDO

Authors Stefano Mancini, S. Mangini, F. Benatti

Publication date 11 March 2020

Published in International Journal of Quantum Information (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/1911.09399

zbMATH Keywords

continuous variable modelsquantum machine learningquantum perceptron

Mathematics Subject Classification ID

NLS equations (nonlinear Schrödinger equations) (35Q55) Data structures (68P05) Quantum measurement theory, state operations, state preparations (81P15) Quantum coherence, entanglement, quantum correlations (81P40) Quantum computation (81P68) Coherent states (81R30)

Abstract: We present a model of Continuous Variable Quantum Perceptron (CVQP) whose architecture implements a classical perceptron. The necessary non-linearity is obtained via measuring the output qubit and using the measurement outcome as input to an activation function. The latter is chosen to be the so-called ReLu activation function by virtue of its practical feasibility and the advantages it provides in learning tasks. The encoding of classical data into realistic finitely squeezed states and the use of superposed (entangled) input states for specific binary problems are discussed.

Recommendations

• A QUANTUM PERCEPTRON
• Pattern capacity of a single quantum perceptron
• Simulating a perceptron on a quantum computer
• Quantum perceptron over a field and neural network architecture selection in a quantum computer
• Continuous-variable deep quantum neural networks for flexible learning of structured classical information

Cites work

• Deep learning
• scientific article; zbMATH DE number 5835674 (Why is no real title available?)
• Quantum Computation over Continuous Variables
• Quantum machine learning. What quantum computing means to data mining
• Quantum machine learning: a classical perspective
• Supervised learning with quantum computers

Cited in

(6)

• Continuous-variable and hybrid quantum gates
• Pattern capacity of a single quantum perceptron
• Continuous-variable deep quantum neural networks for flexible learning of structured classical information
• On the capacity of a quantum perceptron for storing biased patterns
• Quantum optical model of an artificial neuron
• Pseudo quantum advantages in perceptron storage capacity

This page was built for publication: Continuous variable quantum perceptron

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5219353)