Simulating a perceptron on a quantum computer

Abstract

Perceptrons are the basic computational unit of artificial neural networks, as they model the activation mechanism of an output neuron due to incoming signals from its neighbours. As linear classifiers, they play an important role in the foundations of machine learning. In the context of the emerging field of quantum machine learning, several attempts have been made to develop a corresponding unit using quantum information theory. Based on the quantum phase estimation algorithm, this paper introduces a quantum perceptron model imitating the step-activation function of a classical perceptron. This scheme requires resources in $\mathcal{O}(n)$ (where $n$ is the size of the input) and promises efficient applications for more complex structures such as trainable quantum neural networks.

11 pages, 6 figures, accepted by Physics Letters A

References in corpus (6)

• Elementary gates for quantum computation
• The quest for a Quantum Neural Network
• The physics of forgetting: Landauer's erasure principle and information theory
• Quantum neural network
• A Quantum Model for Autonomous Learning Automata
• Autonomous Quantum Perceptron Neural Network

Cited by in corpus (45)

• Efficient Learning for Deep Quantum Neural Networks
• Continuous-variable quantum neural networks
• Prediction by linear regression on a quantum computer
• An Artificial Neuron Implemented on an Actual Quantum Processor
• Is quantum advantage the right goal for quantum machine learning?
• Quantum Machine Learning for Chemistry and Physics
• Quantum Algorithm for Linear Regression
• Quantum singular value decomposition of non-sparse low-rank matrices
• Quantum computing models for artificial neural networks
• Quantum implementation of an artificial feed-forward neural network
• Nonlinear Quantum Neuron: A Fundamental Building Block for Quantum Neural Networks
• Variational learning for quantum artificial neural networks
• Advances in quantum machine learning
• Quantum Superposition Inspired Spiking Neural Network
• A Simple Quantum Neural Net with a Periodic Activation Function
• Quantum computing model of an artificial neuron with continuously valued input data
• A steady state quantum classifier
• The Quantum Path Kernel: a Generalized Quantum Neural Tangent Kernel for Deep Quantum Machine Learning
• Quantum neural networks force fields generation
• A duplication-free quantum neural network for universal approximation
• Supervised Learning with Quantum Measurements
• Quantum version of the k-NN classifier based on a quantum sorting algorithm
• Scalable Qubit Representations of Neutrino Mixing Matrices
• Classical Artificial Neural Network Training Using Quantum Walks as a Search Procedure
• Quantifying scrambling in quantum neural networks
• Fitting a Collider in a Quantum Computer: Tackling the Challenges of Quantum Machine Learning for Big Datasets
• A Quantum Model for Multilayer Perceptron
• Realization of a quantum neural network using repeat-until-success circuits in a superconducting quantum processor
• Image Classification via Quantum Machine Learning
• A quantum collisional classifier driven by information reservoir
• Quantum Walk to Train a Classical Artificial Neural Network
• Universal quantum gates, artificial neurons and pattern recognition simulated by \textit{LC} resonators
• Implementing perceptron models with qubits
• Weighted Graph Theory Representation of Quantum Information Inspired by Lie Algebras
• Nondestructive classification of quantum states using an algorithmic quantum computer
• A Universal Quantum Circuit Design for Periodical Functions
• Neural Networks Architecture Evaluation in a Quantum Computer
• Can biological quantum networks solve NP-hard problems?
• Multi-Valued Quantum Neurons
• Quadratic Quantum Speedup for Perceptron Training
• Multi-qubits and Polyvalent Singularity in Type II Supestring Theory
• Quantum Deformed Neural Networks
• A Quantum Convolutional Neural Network for Image Classification
• Quantum Algorithms for State Preparation and Data Classification based on Stabilizer Codes
• Quantum Perceptron Revisited: Computational-Statistical Tradeoffs