International Conference on Intelligent Control and Information Processing

A Quantum Phase Neuron

Shuang Cong

Published Feb 6, 2025• 0 citations

Abstract

A quantum phase neuron (QPN), including its structural design and the derivation of input-output relationships, is proposed for the first time. The research focuses on the design process of quantum phase neurons when the probability amplitude is a real number. The paper provides the corresponding encoding functions based on different input types, which offers the flexibility for handling complex input data patterns. At the same time, the proposed single-layer QPN is used to solve the XNOR logic operation problem, and the superiority of the proposed QPN in performance is shown. The research presented in this paper demonstrates the potential and application prospects of QPN in constructing high-efficient quantum neural networks.

DOI: 10.1109/icicip64458.2025.10898106

Related papers

A Quantum Phase Neural Network with Multi-Inputs/Single-Output

Shuang Cong, Jinmin Yang, Sajede Harraz

A 35 input/single output quantum phase neural network (QPNN) is proposed to recognize the English letters' A 'and' B 'composed 7*5 of pixels. Each node of the proposed QPNN has the input with 0 or 1. Through normalization and quantum phase encoding, each set of 35 with 0 or 1 digital inputs is encoded into a quantum superposition state described by 35 quantum phases. Then, a quantum rotation gate is used to introduce adjustable phase, and a controlled NOT gate is used to entangle the relative phase between the two inputs. The relationship between the input and output of the network is derived. This paper also derived the phase weight learning training algorithm with adaptive learning rate. The solutions with the recognition probability of 1 is designed, and the analytical expressions for all adjustable phase solutions with zero errors are not unique. The experimental performance is verified on the Qiskit platform. This paper uses phase drive to convert the probability calculation into an analytical polynomial function with adjustable rotation angles in the network, avoiding the bottleneck of generating all 2^35 complex exponential amplitudes and providing an effective way to solve the "exponential wall" problem, which provides a new implementation solution for the practical application of multi-input recognition problems.

quant-pharXiv:2610.00868Oct 2, 20260 citations

Hybrid Quantum Neural Networks Model Algorithm and Simulation

Hong Yu Xiao, Maojun Cao

A quantum neural networks model based on quantum neurons and traditional neurons is presented in this paper. The input of quantum neuron is real vector, its weight is quantum bits, its transforming function is an inner product operator and its output is a real number. The network includes three layers. Input layer is composed of traditional neurons that receive input information. Hidden layer is composed of quantum neurons that extract pattern feature of input information and transfer them to output layer. Output layer is composed of traditional neurons that export calculation result. The weightings of output layer are rectified by back propagation algorithm. The weightings of hidden layer are rectified by a group of quantum gates. A detailed learning algorithm is designed. Finally the availability of the model and algorithm is illustrated by two application examples of pattern recognition and functional approximation.

International Conference on Natural Computation (ICNC)Jan 1, 200911 citations

Quantum Neural Network Based on Swap Test and Phase Estimation

LIU Guangshuo LI Panchi

To address the integration of quantum computing and neural computing, this paper investigates a quantum neural network (QNN) model and its algorithm based on swap test and phase estimation. Firstly, a quantum circuit for swap tests with multi-qubit control is proposed, and a quantum neuron model is developed by combining this with phase estimation. The model uses quantum bits for inputs, weights, and outputs, where the phase of the weight qubits serves as the model parameters. Based on this quantum neuron, a QNN model is constructed, with measurements performed at the network output to obtain real-valued outputs. Various quantum circuits associated with the network model are designed in detail, and the input-output relationships for each network layer are derived according to quantum computing theory. Additionally, a method for adjusting network parameters based on the gradient descent algorithm is thoroughly developed. Finally, simulations are conducted on a classical computer using planar point set recognition and handwritten digit binary classification. Although these simulations do not verify the parallelism of quantum computing, they do validate the model??s execution effectiveness. The results show that the proposed model has a clear advantage in classification performance compared with a classical backpropagation (BP) neural network with the same parameter scale. This demonstrates that constructing QNN models based on multi-qubit swap tests and phase estimation is both effective and feasible, offering a new perspective for future research on quantum neural networks.

Sep 1, 20250 citations

Learning algorithm and application of quantum BP neural networks based on universal quantum gates

Panchi Li, Li Shiyong

A quantum BP neural networks model with learning algorithm is proposed. First, based on the universality of single qubit rotation gate and two-qubit controlled-NOT gate, a quantum neuron model is constructed, which is composed of input, phase rotation, aggregation, reversal rotation and output. In this model, the input is described by qubits, and the output is given by the probability of the state in which |1〉 is observed. The phase rotation and the reversal rotation are performed by the universal quantum gates. Secondly, the quantum BP neural networks model is constructed, in which the output layer and the hide layer are quantum neurons. With the application of the gradient descent algorithm, a learning algorithm of the model is proposed, and the continuity of the model is proved. It is shown that this model and algorithm are superior to the conventional BP networks in three aspects: convergence speed, convergence rate and robustness, by two application examples of pattern recognition and function approximation.

Journal of Systems Engineering and ElectronicsFeb 1, 200868 citations

Design of quantum neuron model for quantum neural networks

Yao Zhang, Qiang Ni

Quantum neural network is a network which is to be composed of several quantum neurons, which is required to have a certain topological structure. In this article, we propose a new method to encode classical input data into quantum states to represent a quantum neuron, which has a low-complexity form and can be easily utilized to construct a quantum neural network. The numerical simulation of two classification tasks with the proposed quantum neuron model is conducted to show its validity.

Quantum EngineeringAug 25, 202110 citations

Quantum Neural Networks: Adaptive Neuron Network Structures

Jincheng Zhang

Quantum Neural Networks (QNNs) represent a novel approach to artificial neural networks, leveraging the unique properties of quantum mechanics to enhance computation capabilities. This paper investigates the design and implementation of a quantum neural network (QNN) that employs adaptive neuron structures, dynamically adjusting their connections based on input data. We explore the potential of quantum entanglement to facilitate this self-adaptive behavior, aiming to achieve improved efficiency and robustness compared to classical neural networks. The core mechanism centers around utilizing quantum entanglement to enable neurons to subtly influence each other's states, promoting a form of self-organization within the network. This research offers a promising avenue for advancing QNNs and opens up new possibilities for complex computational tasks.

Sep 5, 20260 citations