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

International Conference on System Theory, Control and Computing (ICSTCC)

Effects of disabled neurons in classical and quantum networks information processing

Iulian Petrila, Beatrice Luca, Vasile Manta

Published Oct 1, 2016• 1 citation
Publisher

Abstract

In this study, the effects of missing or broken elements on the memory preservation in classical and quantum neural networks are analyzed. The networks were built by considering each node as a bit or qubit neuron-like processing unit. The qubit-neurons are analyzed from two perspectives, one that involves consideration of quantum coupling between them alongside with specific network connections and another that uses only non quantum network connections between them. The same classical architecture and learning are applied to both networks that contain classical and quantum nodes. The analysis of memory preservation in such networks consists in monitoring changes in memory states as results of interruption of different connections between nodes. From this perspective, the comparative classical and quantum network response to broken or missing elements are analyzed, compared and contextualized.

DOI
10.1109/icstcc.2016.7790748

Related papers

Quantum Neural Networks with Non-Markovian Dynamics

Jincheng Zhang

This paper investigates the potential of quantum neural networks (QNNs) enhanced by non-Markovian dynamics. Traditional Markovian QNNs suffer from limitations in capturing long-range dependencies, a crucial aspect in complex data processing. We propose a novel QNN architecture that incorporates quantum memory and entanglement to facilitate non-Markovian information processing. This approach allows the network to retain and utilize the entire past history of the input, fundamentally altering the dynamics of information flow. Through theoretical analysis and mathematical formulations, we demonstrate how this architecture can significantly improve the network's ability to learn and represent complex patterns, particularly those exhibiting long-range correlations. Specifically, we introduce a modified update rule leveraging the concept of quantum memory and entanglement, expressed as: $ \Delta w_{ij} = \alpha \cdot E[\rho(t)|x_1, x_2, ..., x_K] \cdot \langle \psi_i | \rho(t) | \psi_j \rangle - (1 - \alpha) \cdot w_{ij}$ Where: * $ \Delta w_{ij}$ is the change in the synaptic weight between neurons *i* and *j*. * $\alpha$ is the learning rate. * $E[\rho(t)|x_1, x_2, ..., x_K]$ represents the expected state of the quantum memory at time *t*, given the entire input sequence $x_1, x_2, ..., x_K$. * $\rho(t)$ is the density matrix representing the quantum state at time *t*. * $\langle \psi_i | \rho(t) | \psi_j \rangle$ is the inner product between the quantum states $\psi_i$ and $\psi_j$ within the density matrix $\rho(t)$. * $w_{ij}$ is the current synaptic weight between neurons *i* and *j*. The core of our innovation lies in the utilization of quantum memory, modeled as a quantum state $\rho(t)$, which retains information about the entire past sequence. The entanglement between neurons further enables correlated updates, bypassing the limitations of Markovian models that only consider immediate dependencies. We explore the impact of varying the strength of entanglement and the capacity of the quantum memory on the network's performance using mathematical models. The results suggest a significant improvement in accuracy and convergence speed compared to standard Markovian QNNs when dealing with datasets exhibiting long-range dependencies. Further investigation into the scalability and practical implementation of this architecture is warranted.

•Aug 29, 2026•0 citations

Quantum-classical neurons upgraded with optical spin qubits for advanced computing and networking architectures

Osama M. Nayfeh

Hardware neurons incorporating built-in memory components are critical technologies for implementing large scale neural networks that exhibit adaptive-itinerant behavior and produce biological-inspired spiking patterns that match neuroscience known operations (1). Moreover, neurons capable of full quantum information processing through their qubit states and quantum trajectory provides capability for hybrid quantum-classical operations through the level of coherence/entanglement and non-Markovianity (2,3). These attributes further contribute to solving complex quantum mechanical problems by providing a rich and diverse group for expressing quantum neural states. Upgrading these hardware neurons now with optical spin qubits excitable with pulsed laser excitation in the near infrared and designed from negatively charged silicon vacancies in semiconductor silicon carbide (4) and Neodymium rare earth ions in the superconducting Niobium/Niobium oxide film (5) that form the memory provides access to the unique spin Hamiltonian that considers electronic and nuclear interactions. In this manuscript, we experimentally measure opto-electronic quantum-classical neurons integrated with a optical spin qubit and examine how tailored neuronal spiking sequences drive the photoluminescence oscillations and modulate the quantum spin transitions. We derive a quantum model for the system that considers the interaction between the neuron and optical qubit spin and perform calculations to project how quantum computing operations are expandable across the state space in the quantum-classical neuron and spin qubit system. For example, the resulting impact on the neuron quantum states where the strength is adjustable due to dynamical memory changes. These results are critical for realizing hardware neurons with quantum optical capabilities and inspired by the existence in biology of biophotons.

quant-pharXiv:2607.11992•Jul 14, 2026

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•226 citations

Exploration of Quantum Neural Architecture by Mixing Quantum Neuron Designs: (Invited Paper)

Zhepeng Wang, Zhiding Liang, Shanglin Zhou +3 more

With the constant increase of the number of quantum bits (qubits) in the actual quantum computers, implementing and accelerating the prevalent deep learning on quantum computers are becoming possible. Along with this trend, there emerge quantum neural architectures based on different designs of quantum neurons. A fundamental question in quantum deep learning arises: what is the best quantum neural architecture? Inspired by the design of neural architectures for classical computing which typically employs multiple types of neurons, this paper makes the very first attempt to mix quantum neuron designs to build quantum neural architectures. We observe that the existing quantum neuron designs may be quite different but complementary, such as neurons from variational quantum circuits (VQC) and Quantumflow. More specifically, VQC can apply real-valued weights but suffer from being extended to multiple layers, while QuantumFlow can build a multi-layer network efficiently, but is limited to use binary weights. To take their respective advantages, we propose to mix them together and figure out a way to connect them seamlessly without additional costly measurement. We further investigate the design principles to mix quantum neurons, which can provide guidance for quantum neural architecture exploration in the future. Experimental results demonstrate that the identified quantum neural architectures with mixed quantum neurons can achieve 90.62% of accuracy on the MNIST dataset, compared with 52.77% and 69.92% on the VQC and QuantumFlow, respectively.

arXiv:2109.03806•International Conference on Computer Aided Design•Nov 1, 2021•28 citations

The Design and Implementation of Quantum-Inspired Neural Networks

Yang Shu-yu

The approximation ability of neural networks plays an important role to the result when one uses neural networks to resolve problems.Unfortunately there is no ideal way to construct proper networks with strong approximation ability.A novel construction approach based on the multi-qubits controller-not gates is proposed for neural networks model in this paper.The proposed model consists of three layers where the hidden nodes are the quantum neurons and the output nodes are the common neurons.The quantum neuron consists of the quantum rotation gates and the multi-qubits controllednot gates.The overall memory of input sequences is captured from information feedback of target qubit from output to input in the multi-qubits controlled-not gate.The output of quantum neuron is obtained from the controlled relationship of the multi-qubits controlled-not gate.The L-M learning algorithms are designed in detail based on the basic principles of quantum computation.The features of input sequences can be effectively obtained in two ways of breadth and depth.The experimental results of solitaire forecast show that,when the number of input nodes is close to the length of sequences,the training set recognition rate of the proposed model increases about 8% than the common neural networks,which reveals the effectiveness of the quantum computation for enhancing the approximation capability of the common neural networks.

Journal of Signal Processing•Jan 1, 2014•0 citations

Neural Networks with c-NOT Gated Nodes

Fariel Shafee

We try to design a quantum neural network with qubits instead of classical neurons with deterministic states, and also with quantum operators replacing teh classical action potentials. With our choice of gates interconnecting teh neural lattice, it appears that the state of the system behaves in ways reflecting both the strengths of coupling between neurons as well as initial conditions. We find that depending whether there is a threshold for emission from excited to ground state, the system shows either aperiodic oscillations or coherent ones with periodicity depending on the strength of coupling.

arXiv:quant-ph/0202016•Feb 2, 2002•10 citations
In this study, the effects of missing or broken elements on the memory preservation in classical and quantum neural networks are analyzed. The networks were built by considering each node as a bit or qubit neuron-like processing unit. The qubit-neurons are analyzed from two perspectives, one that involves consideration of quantum coupling between them alongside with specific network connections and another that uses only non quantum network connections between them. The same classical architecture and learning are applied to both networks that contain classical and quantum nodes. The analysis of memory preservation in such networks consists in monitoring changes in memory states as results of interruption of different connections between nodes. From this perspective, the comparative classical and quantum network response to broken or missing elements are analyzed, compared and contextualized.
This paper investigates the potential of quantum neural networks (QNNs) enhanced by non-Markovian dynamics. Traditional Markovian QNNs suffer from limitations in capturing long-range dependencies, a crucial aspect in complex data processing. We propose a novel QNN architecture that incorporates quantum memory and entanglement to facilitate non-Markovian information processing. This approach allows the network to retain and utilize the entire past history of the input, fundamentally altering the dynamics of information flow. Through theoretical analysis and mathematical formulations, we demonstrate how this architecture can significantly improve the network's ability to learn and represent complex patterns, particularly those exhibiting long-range correlations. Specifically, we introduce a modified update rule leveraging the concept of quantum memory and entanglement, expressed as: $ \Delta w_{ij} = \alpha \cdot E[\rho(t)|x_1, x_2, ..., x_K] \cdot \langle \psi_i | \rho(t) | \psi_j \rangle - (1 - \alpha) \cdot w_{ij}$ Where: * $ \Delta w_{ij}$ is the change in the synaptic weight between neurons *i* and *j*. * α\alphaα is the learning rate. * E[ρ(t)∣x1,x2,...,xK]E[\rho(t)|x_1, x_2, ..., x_K]E[ρ(t)∣x1​,x2​,...,xK​] represents the expected state of the quantum memory at time *t*, given the entire input sequence x1,x2,...,xKx_1, x_2, ..., x_Kx1​,x2​,...,xK​. * ρ(t)\rho(t)ρ(t) is the density matrix representing the quantum state at time *t*. * ⟨ψi∣ρ(t)∣ψj⟩\langle \psi_i | \rho(t) | \psi_j \rangle⟨ψi​∣ρ(t)∣ψj​⟩ is the inner product between the quantum states ψi\psi_iψi​ and ψj\psi_jψj​ within the density matrix ρ(t)\rho(t)ρ(t). * wijw_{ij}wij​ is the current synaptic weight between neurons *i* and *j*. The core of our innovation lies in the utilization of quantum memory, modeled as a quantum state ρ(t)\rho(t)ρ(t), which retains information about the entire past sequence. The entanglement between neurons further enables correlated updates, bypassing the limitations of Markovian models that only consider immediate dependencies. We explore the impact of varying the strength of entanglement and the capacity of the quantum memory on the network's performance using mathematical models. The results suggest a significant improvement in accuracy and convergence speed compared to standard Markovian QNNs when dealing with datasets exhibiting long-range dependencies. Further investigation into the scalability and practical implementation of this architecture is warranted.
Hardware neurons incorporating built-in memory components are critical technologies for implementing large scale neural networks that exhibit adaptive-itinerant behavior and produce biological-inspired spiking patterns that match neuroscience known operations (1). Moreover, neurons capable of full quantum information processing through their qubit states and quantum trajectory provides capability for hybrid quantum-classical operations through the level of coherence/entanglement and non-Markovianity (2,3). These attributes further contribute to solving complex quantum mechanical problems by providing a rich and diverse group for expressing quantum neural states. Upgrading these hardware neurons now with optical spin qubits excitable with pulsed laser excitation in the near infrared and designed from negatively charged silicon vacancies in semiconductor silicon carbide (4) and Neodymium rare earth ions in the superconducting Niobium/Niobium oxide film (5) that form the memory provides access to the unique spin Hamiltonian that considers electronic and nuclear interactions. In this manuscript, we experimentally measure opto-electronic quantum-classical neurons integrated with a optical spin qubit and examine how tailored neuronal spiking sequences drive the photoluminescence oscillations and modulate the quantum spin transitions. We derive a quantum model for the system that considers the interaction between the neuron and optical qubit spin and perform calculations to project how quantum computing operations are expandable across the state space in the quantum-classical neuron and spin qubit system. For example, the resulting impact on the neuron quantum states where the strength is adjustable due to dynamical memory changes. These results are critical for realizing hardware neurons with quantum optical capabilities and inspired by the existence in biology of biophotons.
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.
With the constant increase of the number of quantum bits (qubits) in the actual quantum computers, implementing and accelerating the prevalent deep learning on quantum computers are becoming possible. Along with this trend, there emerge quantum neural architectures based on different designs of quantum neurons. A fundamental question in quantum deep learning arises: what is the best quantum neural architecture? Inspired by the design of neural architectures for classical computing which typically employs multiple types of neurons, this paper makes the very first attempt to mix quantum neuron designs to build quantum neural architectures. We observe that the existing quantum neuron designs may be quite different but complementary, such as neurons from variational quantum circuits (VQC) and Quantumflow. More specifically, VQC can apply real-valued weights but suffer from being extended to multiple layers, while QuantumFlow can build a multi-layer network efficiently, but is limited to use binary weights. To take their respective advantages, we propose to mix them together and figure out a way to connect them seamlessly without additional costly measurement. We further investigate the design principles to mix quantum neurons, which can provide guidance for quantum neural architecture exploration in the future. Experimental results demonstrate that the identified quantum neural architectures with mixed quantum neurons can achieve 90.62% of accuracy on the MNIST dataset, compared with 52.77% and 69.92% on the VQC and QuantumFlow, respectively.
The approximation ability of neural networks plays an important role to the result when one uses neural networks to resolve problems.Unfortunately there is no ideal way to construct proper networks with strong approximation ability.A novel construction approach based on the multi-qubits controller-not gates is proposed for neural networks model in this paper.The proposed model consists of three layers where the hidden nodes are the quantum neurons and the output nodes are the common neurons.The quantum neuron consists of the quantum rotation gates and the multi-qubits controllednot gates.The overall memory of input sequences is captured from information feedback of target qubit from output to input in the multi-qubits controlled-not gate.The output of quantum neuron is obtained from the controlled relationship of the multi-qubits controlled-not gate.The L-M learning algorithms are designed in detail based on the basic principles of quantum computation.The features of input sequences can be effectively obtained in two ways of breadth and depth.The experimental results of solitaire forecast show that,when the number of input nodes is close to the length of sequences,the training set recognition rate of the proposed model increases about 8% than the common neural networks,which reveals the effectiveness of the quantum computation for enhancing the approximation capability of the common neural networks.
We try to design a quantum neural network with qubits instead of classical neurons with deterministic states, and also with quantum operators replacing teh classical action potentials. With our choice of gates interconnecting teh neural lattice, it appears that the state of the system behaves in ways reflecting both the strengths of coupling between neurons as well as initial conditions. We find that depending whether there is a threshold for emission from excited to ground state, the system shows either aperiodic oscillations or coherent ones with periodicity depending on the strength of coupling.