Challenges
Datasets
Workspaces
Papers
Discussions
Leaderboard
Log inSign up
Challenges
Datasets
Workspaces
Papers
Discussions
Leaderboard
Blog
Job Board
Q3AS

© 2026 Aqora Quantum S.A.S.

TermsPrivacyLegal Notice

arXiv:1806.09664

Artificial Quantum Neural Network: quantum neurons, logical elements and tests of convolutional nets

V. I. Dorozhinsky, Oleg Pavlovsky

Published Jun 25, 2018• 3 citations
arXivHTMLPDF

Abstract

We consider a model of an artificial neural network that uses quantum-mechanical particles in a two-humped potential as a neuron. To simulate such a quantum-mechanical system the Monte-Carlo integration method is used. A form of the self-potential of a particle and two potentials (exciting and inhibiting) interaction are proposed. The possibility of implementing the simplest logical elements, (such as AND, OR and NOT) based on introduced quantum particles is shown. Further we show implementation of a simplest convolutional network. Finally we construct a network that recognizes handwritten symbols, which shows that in the case of simple architectures, it is possible to transfer weights from a classical network to a quantum one.

DOI
10.48550/arxiv.1806.09664

Related papers

Artificial stochastic neural network on the base of double quantum wells

Oleg Pavlovsky, V. I. Dorozhinsky, S. D. Mostovoy

In this paper, we consider a model of an artificial neural network based on quantum-mechanical particles in [Formula: see text] potential. These particles play the role of neurons in our model. To simulate such a quantum-mechanical system, the Monte Carlo integration method is used. A form of the self-potential of a particle as well as two interaction potentials (exciting and inhibiting) are proposed. Examples of simplest logical elements (such as AND, OR and NOT) are shown. Further, we show an implementation of the simplest convolutional network in framework of our model.

arXiv:2208.07584•Modern Physics Letters B•Nov 19, 2021•0 citations

Quantum-Mechanical Model of Neural Network Elements

Alexander Novoselov, Oleg Pavlovsky

A model of a neural-network-like quantum-mechanical system is considered. The role of neurons is played by quantum-mechanical particles which evolve under the action of an external double-well potential. An instanton is used as a spike. Neurons are connected by the interaction potential $${{V}_{{{\text{int}}}}}({{\hat {q}}_{i}},{{\hat {q}}_{j}})$$ . The connection is directional owing to asymmetry of the interaction potential. Therefore, the complete Hamiltonian of the system is $$\hat {H} = \sum\nolimits_i \left( {\frac{1}{2}\hat {p}_{i}^{2} + {{V}_{0}}({{{\hat {q}}}_{i}})} \right) + \sum\nolimits_{i > j} \,{{V}_{{{\text{int}}}}}({{\hat {q}}_{i}},{{\hat {q}}_{j}})$$ . The system is investigated by the path integral Monte Carlo (PIMC) method. It is shown that with a certain choice of parameters in this system it is possible to transfer activity in long chains of neurons.

Physics of Atomic Nuclei•Dec 1, 2020•0 citations

Building quantum neural networks based on a swap test

Jian Zhao, Yuanhang Zhang, Changpeng Shao +3 more

An artificial neural network, consisting of many neurons in different layers, is an important method to simulate the human brain. Usually, one neuron has two operations: one is linear, the other is nonlinear. The linear operation is the inner product and the nonlinear operation is represented by an activation function. In this work, we introduce a kind of quantum neuron whose inputs and outputs are quantum states. The inner product and activation operator of the quantum neurons can be realized by quantum circuits. Based on the quantum neuron, we propose a model of a quantum neural network in which the weights between neurons are all quantum states. We also construct a quantum circuit to realize this quantum neural network model. A learning algorithm is proposed meanwhile. We show the validity of the learning algorithm theoretically and demonstrate the potential of the quantum neural network numerically.

arXiv:1904.12697•Physical Review A•Jul 23, 2019•59 citations

Quantum Neuron: an elementary building block for machine learning on quantum computers

Yudong Cao, Gian Giacomo Guerreschi, Alán Aspuru‐Guzik

Even the most sophisticated artificial neural networks are built by aggregating substantially identical units called neurons. A neuron receives multiple signals, internally combines them, and applies a non-linear function to the resulting weighted sum. Several attempts to generalize neurons to the quantum regime have been proposed, but all proposals collided with the difficulty of implementing non-linear activation functions, which is essential for classical neurons, due to the linear nature of quantum mechanics. Here we propose a solution to this roadblock in the form of a small quantum circuit that naturally simulates neurons with threshold activation. Our quantum circuit defines a building block, the "quantum neuron", that can reproduce a variety of classical neural network constructions while maintaining the ability to process superpositions of inputs and preserve quantum coherence and entanglement. In the construction of feedforward networks of quantum neurons, we provide numerical evidence that the network not only can learn a function when trained with superposition of inputs and the corresponding output, but that this training suffices to learn the function on all individual inputs separately. When arranged to mimic Hopfield networks, quantum neural networks exhibit properties of associative memory. Patterns are encoded using the simple Hebbian rule for the weights and we demonstrate attractor dynamics from corrupted inputs. Finally, the fact that our quantum model closely captures (traditional) neural network dynamics implies that the vast body of literature and results on neural networks becomes directly relevant in the context of quantum machine learning.

arXiv:1711.11240•Nov 30, 2017•113 citations

AN INTRODUCTION TO QUANTUM NEURAL COMPUTING

Shaktikanta Nayak, Sitakanta Nayak, Jaskaran Singh

The goal of the artificial neural network is to create powerful artificial problem solving systems. The field of quantum computation applies ideas from quantum mechanics to the study of computation and has made interesting progress. Quantum Neural Network (QNN) is one of the new paradigms built upon the combination of classical neural computation and quantum computation. It is argued that the study of QNN may explain the brain functionality in a better way and create new systems for information processing including solving some classically intractable problems. In this paper we have given an introductory representation of quantum artificial neural network to show how it can be modelled on the basis of double-slit experiment. Also an attempt is made to show the quantum mechanical representation of a classical neuron to implement Hadamard transformation.

Journal of Global Research in Computer Sciences•Sep 14, 2011•8 citations

Based on Quantum Mechanics Simulation of Neurons Model (QMNN)

Jincheng Zhang

This paper introduces the Quantum Mechanics Simulation of Neurons Model (QMNN), a novel approach to simulating neuronal behavior based on fundamental principles of quantum mechanics. Traditional artificial neural networks (ANNs) often struggle to accurately replicate the complex dynamics observed in biological neurons due to their reliance on classical computational methods. QMNN leverages concepts such as superposition and entanglement, key features of quantum mechanics, to represent neuronal states and interactions. The model employs a discrete quantum system, where neuronal activity is represented by quantum states, allowing for inherent parallelism and potentially capturing phenomena currently inaccessible to classical neural simulations. This work details the core concepts of QMNN, outlining its mathematical formulation, key components, and potential advantages over conventional ANN approaches. We present a simplified model of a single neuron utilizing a quantum bit (qubit) to represent its state. The model's equations reflect the Schrödinger equation and the evolution of quantum states under influence of external stimuli. The simulation explores scenarios demonstrating the potential for increased computational efficiency and the ability to model phenomena like quantum coherence within neuronal networks. Further research will focus on scaling the model to multi-neuron networks and investigating the model's applicability to various neurological conditions.

•Sep 7, 2026•0 citations
We consider a model of an artificial neural network that uses quantum-mechanical particles in a two-humped potential as a neuron. To simulate such a quantum-mechanical system the Monte-Carlo integration method is used. A form of the self-potential of a particle and two potentials (exciting and inhibiting) interaction are proposed. The possibility of implementing the simplest logical elements, (such as AND, OR and NOT) based on introduced quantum particles is shown. Further we show implementation of a simplest convolutional network. Finally we construct a network that recognizes handwritten symbols, which shows that in the case of simple architectures, it is possible to transfer weights from a classical network to a quantum one.
In this paper, we consider a model of an artificial neural network based on quantum-mechanical particles in [Formula: see text] potential. These particles play the role of neurons in our model. To simulate such a quantum-mechanical system, the Monte Carlo integration method is used. A form of the self-potential of a particle as well as two interaction potentials (exciting and inhibiting) are proposed. Examples of simplest logical elements (such as AND, OR and NOT) are shown. Further, we show an implementation of the simplest convolutional network in framework of our model.
A model of a neural-network-like quantum-mechanical system is considered. The role of neurons is played by quantum-mechanical particles which evolve under the action of an external double-well potential. An instanton is used as a spike. Neurons are connected by the interaction potential Vint(q^i,q^j){{V}_{{{\text{int}}}}}({{\hat {q}}_{i}},{{\hat {q}}_{j}})Vint​(q^​i​,q^​j​) . The connection is directional owing to asymmetry of the interaction potential. Therefore, the complete Hamiltonian of the system is H^=∑i(12p^i2+V0(q^i))+∑i>j Vint(q^i,q^j)\hat {H} = \sum\nolimits_i \left( {\frac{1}{2}\hat {p}_{i}^{2} + {{V}_{0}}({{{\hat {q}}}_{i}})} \right) + \sum\nolimits_{i > j} \,{{V}_{{{\text{int}}}}}({{\hat {q}}_{i}},{{\hat {q}}_{j}})H^=∑i​(21​p^​i2​+V0​(q^​i​))+∑i>j​Vint​(q^​i​,q^​j​) . The system is investigated by the path integral Monte Carlo (PIMC) method. It is shown that with a certain choice of parameters in this system it is possible to transfer activity in long chains of neurons.
An artificial neural network, consisting of many neurons in different layers, is an important method to simulate the human brain. Usually, one neuron has two operations: one is linear, the other is nonlinear. The linear operation is the inner product and the nonlinear operation is represented by an activation function. In this work, we introduce a kind of quantum neuron whose inputs and outputs are quantum states. The inner product and activation operator of the quantum neurons can be realized by quantum circuits. Based on the quantum neuron, we propose a model of a quantum neural network in which the weights between neurons are all quantum states. We also construct a quantum circuit to realize this quantum neural network model. A learning algorithm is proposed meanwhile. We show the validity of the learning algorithm theoretically and demonstrate the potential of the quantum neural network numerically.
Even the most sophisticated artificial neural networks are built by aggregating substantially identical units called neurons. A neuron receives multiple signals, internally combines them, and applies a non-linear function to the resulting weighted sum. Several attempts to generalize neurons to the quantum regime have been proposed, but all proposals collided with the difficulty of implementing non-linear activation functions, which is essential for classical neurons, due to the linear nature of quantum mechanics. Here we propose a solution to this roadblock in the form of a small quantum circuit that naturally simulates neurons with threshold activation. Our quantum circuit defines a building block, the "quantum neuron", that can reproduce a variety of classical neural network constructions while maintaining the ability to process superpositions of inputs and preserve quantum coherence and entanglement. In the construction of feedforward networks of quantum neurons, we provide numerical evidence that the network not only can learn a function when trained with superposition of inputs and the corresponding output, but that this training suffices to learn the function on all individual inputs separately. When arranged to mimic Hopfield networks, quantum neural networks exhibit properties of associative memory. Patterns are encoded using the simple Hebbian rule for the weights and we demonstrate attractor dynamics from corrupted inputs. Finally, the fact that our quantum model closely captures (traditional) neural network dynamics implies that the vast body of literature and results on neural networks becomes directly relevant in the context of quantum machine learning.
The goal of the artificial neural network is to create powerful artificial problem solving systems. The field of quantum computation applies ideas from quantum mechanics to the study of computation and has made interesting progress. Quantum Neural Network (QNN) is one of the new paradigms built upon the combination of classical neural computation and quantum computation. It is argued that the study of QNN may explain the brain functionality in a better way and create new systems for information processing including solving some classically intractable problems. In this paper we have given an introductory representation of quantum artificial neural network to show how it can be modelled on the basis of double-slit experiment. Also an attempt is made to show the quantum mechanical representation of a classical neuron to implement Hadamard transformation.
This paper introduces the Quantum Mechanics Simulation of Neurons Model (QMNN), a novel approach to simulating neuronal behavior based on fundamental principles of quantum mechanics. Traditional artificial neural networks (ANNs) often struggle to accurately replicate the complex dynamics observed in biological neurons due to their reliance on classical computational methods. QMNN leverages concepts such as superposition and entanglement, key features of quantum mechanics, to represent neuronal states and interactions. The model employs a discrete quantum system, where neuronal activity is represented by quantum states, allowing for inherent parallelism and potentially capturing phenomena currently inaccessible to classical neural simulations. This work details the core concepts of QMNN, outlining its mathematical formulation, key components, and potential advantages over conventional ANN approaches. We present a simplified model of a single neuron utilizing a quantum bit (qubit) to represent its state. The model's equations reflect the Schrödinger equation and the evolution of quantum states under influence of external stimuli. The simulation explores scenarios demonstrating the potential for increased computational efficiency and the ability to model phenomena like quantum coherence within neuronal networks. Further research will focus on scaling the model to multi-neuron networks and investigating the model's applicability to various neurological conditions.