Continuous Variable Quantum Perceptron

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.

arXiv comment16 pages, 2 figures

References in corpus (6)

• Quantum computation over continuous variables
• Quantum machine learning: a classical perspective
• Efficient Classical Simulation of Continuous Variable Quantum Information Processes
• Strawberry Fields: A Software Platform for Photonic Quantum Computing
• An Artificial Neuron Implemented on an Actual Quantum Processor
• Schrodinger cats and their power for quantum information processing

Cited by in corpus (8)

• Is quantum advantage the right goal for quantum machine learning?
• Opportunities in Quantum Reservoir Computing and Extreme Learning Machines
• Pattern capacity of a single quantum perceptron
• Dissipative Quantum Hopfield Network: A numerical analysis
• Quantum optical classifier with superexponential speedup
• On the capacity of a quantum perceptron for storing biased patterns
• Quantum optical shallow networks
• Pseudo quantum advantages in perceptron storage capacity