Continuous Variable Quantum Perceptron

TL;DR

This paper introduces a Continuous Variable Quantum Perceptron model that mimics classical perceptrons using quantum states, measurement-based non-linearity, and ReLu activation, enabling quantum-enhanced learning tasks.

Contribution

It proposes a novel quantum perceptron architecture utilizing continuous variables, measurement-based non-linearity, and realistic data encoding methods.

Findings

Implementation of a quantum perceptron with ReLu activation

Use of finitely squeezed states for data encoding

Potential advantages in quantum learning tasks

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.