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 Joint Conference on Neural Networks (IJCNN)

Time Series Prediction by Quaternionic Qubit Neural Network

Takuya Teguri, Teijiro Isokawa, Nobuyuki Matsui, H. Nishimura, Naotake Kamiura

Published Jul 1, 2020• 7 citations
Publisher

Abstract

We propose a neural network model based on quantum information processing with quaternionic representation and operations, called Quaternionic Qubit Neural Network. The state of a neuron is represented by a point on the Bloch sphere with incorporating quaternionic representation. The operations for this neuron also follow the operations in quaternions. The proposed neural networks are evaluated through numerical experiments for predicting chaotic time series produced by a Lorentz system. They have better performances in predicting long-term series, as compared to conventional (real-valued) neural networks.

DOI
10.1109/ijcnn48605.2020.9207208

Related papers

Chaotic time series prediction by qubit neural network with complex-valued representation

Taisei Ueguchi, Nobuyuki Matsui, Teijiro Isokawa

A qubit neural network (QNN) is a neural network that incorporates the quantum computing and representation. QNN is constructed from a set of qubit neuron model, of which internal state is a coherent superposition of qubit states. This paper evaluates the performance of QNN through a prediction of well-known Lorentz attractor, which produces chaotic time series by three dynamical systems. The experimental results show that QNN can predict time series more precisely, compared with conventional (real-valued) neural networks.

Annual Conference of the Society of Instrument and Control Engineers of Japan (SICE)•Sep 1, 2016•10 citations

Quaternion quantum neurocomputing

Eduardo Jose Bayro-Corrochano, Samuel Solis-Gamboa

Since the introduction of quaternion by Hamilton in 1843, quaternions have been used in a lot of applications. One of the most interesting qualities is that we can use quaternions to carry out rotations and operate on other quaternions; this characteristic of the quaternions inspired us to investigate how the quantum states and quantum operator work in the field of quaternions and how we can use it to construct a quantum neural network. This new type of quantum neural network (QNN) is developed in the quaternion algebra framework that is isomorphic to the rotor algebra [Formula: see text] of the geometric algebra and is based on the so-called qubit neuron model. The quaternion quantum neural network (QQNN) is tested and shows robust performance.

International Journal of Wavelets Multiresolution and Information Processing•May 31, 2020•6 citations

Qubit Neural Network

Nobuyuki Matsui, H. Nishimura, Teijiro Isokawa

Recently, quantum neural networks have been explored as one of the candidates for improving the computational efficiency of neural networks. In this chapter, after giving a brief review of quantum computing, the authors introduce our qubit neural network, which is a multi-layered neural network composed of quantum bit neurons. In this description, it is indispensable to use the complex-valued representation, which is based on the concept of quantum bit (qubit). By means of the simulations in solving the parity check problems as a bench mark examination, we show that the computational power of the qubit neural network is superior to that of the conventional complex-valued and real-valued neural networks. Furthermore, the authors explore its applications such as image processing and pattern recognition. Thus they clarify that this model outperforms the conventional neural networks.

IGI Global eBooks•Jan 1, 2009•15 citations

Hybrid Quantum-Classical Recurrent Neural Networks for Time Series Prediction

Andrea Ceschini, Antonello Rosato, Massimo Panella

This paper aims at solving time series prediction problems by means of a hybrid quantum-classical recurrent neural network. We propose a novel architecture based on stacked Long Short-Term Memory layers and a variational quantum layer. The latter employs a quantum feature map to embed input data into quantum states, which are then processed by a circuit ansatz. Finally, the expectation value of the circuit's outcome is taken over Pauli observables. Quantum properties such as superposition and entanglement are exploited to perform computations efficiently in a high-dimensional feature space. The proposed hybrid quantum-classical neural network is applied to a real-life challenging problem pertaining to the prediction of renewable energy time series. The comparison between the proposed approach and the classical counterpart shows that the former achieves better results in terms of prediction error, thus demonstrating better approximation of stochastic fluctuations and an overall effectiveness of the quantum variational approach also for prediction tasks.

International Joint Conference on Neural Networks (IJCNN)•Jul 18, 2022•34 citations

Time-Series Forecasting Using Continuous Variables-Based Quantum Neural Networks

Prabhat Anand, M Girish Chandra, Ankit Khandelwal

Continuous Variable-based Quantum Computing (CVQC) has been developing at speed with a lot of promise in the field of quantum machine learning. It provides a direct and natural way to accommodate continuous values into the quantum computing framework. We carried out experiments on quantum simulators where we compared the results of time series forecasting on a type of continuous-variable quantum variational circuit, called CV-Quantum Neural Networks (CVQNN) for different types of time series like Energy Consumption data and stock price data. We compared their performance with a discrete variable-based variational quantum algorithm as well as with a classical Neural Network. Experiments showed that CVQNN can function just like a neural network but with a lesser number of parameters while tackling the two obstacles that are faced in qubit-based computing, which are, tackling continuous values and introducing controlled non-linearity into the circuits. We used the circuit for multi-step forecasting that performed better for a larger prediction window than one-step forecasting done iteratively on the predicted data. The resembling architecture of CVQNN with that of a neural network offers the flexibility of using a similar structure for both one-step and multi-step forecasting.

International Conference on Communication Systems & Networks (COMSNETS)•Jan 3, 2024•4 citations

Time series forecasting with Qubit Neural Networks

Carlos R. B. Azevedo, Tiago A. E. Ferreira

This paper proposes a quantum learning scheme approach for time series forecasting, through the application of the new non-standard Qubit Neural Network (QNN) model. The QNN description was adapted in this work in order to resemble classical Artificial Neural Networks (ANNs). Three stock market series were predicted. The results are discussed over several statistics and are compared with ANNs experiments with equivalent degrees of freedom.

International Conference on Artificial Intelligence and Soft Computing•Aug 9, 2007•5 citations
We propose a neural network model based on quantum information processing with quaternionic representation and operations, called Quaternionic Qubit Neural Network. The state of a neuron is represented by a point on the Bloch sphere with incorporating quaternionic representation. The operations for this neuron also follow the operations in quaternions. The proposed neural networks are evaluated through numerical experiments for predicting chaotic time series produced by a Lorentz system. They have better performances in predicting long-term series, as compared to conventional (real-valued) neural networks.
A qubit neural network (QNN) is a neural network that incorporates the quantum computing and representation. QNN is constructed from a set of qubit neuron model, of which internal state is a coherent superposition of qubit states. This paper evaluates the performance of QNN through a prediction of well-known Lorentz attractor, which produces chaotic time series by three dynamical systems. The experimental results show that QNN can predict time series more precisely, compared with conventional (real-valued) neural networks.
Since the introduction of quaternion by Hamilton in 1843, quaternions have been used in a lot of applications. One of the most interesting qualities is that we can use quaternions to carry out rotations and operate on other quaternions; this characteristic of the quaternions inspired us to investigate how the quantum states and quantum operator work in the field of quaternions and how we can use it to construct a quantum neural network. This new type of quantum neural network (QNN) is developed in the quaternion algebra framework that is isomorphic to the rotor algebra [Formula: see text] of the geometric algebra and is based on the so-called qubit neuron model. The quaternion quantum neural network (QQNN) is tested and shows robust performance.
Recently, quantum neural networks have been explored as one of the candidates for improving the computational efficiency of neural networks. In this chapter, after giving a brief review of quantum computing, the authors introduce our qubit neural network, which is a multi-layered neural network composed of quantum bit neurons. In this description, it is indispensable to use the complex-valued representation, which is based on the concept of quantum bit (qubit). By means of the simulations in solving the parity check problems as a bench mark examination, we show that the computational power of the qubit neural network is superior to that of the conventional complex-valued and real-valued neural networks. Furthermore, the authors explore its applications such as image processing and pattern recognition. Thus they clarify that this model outperforms the conventional neural networks.
This paper aims at solving time series prediction problems by means of a hybrid quantum-classical recurrent neural network. We propose a novel architecture based on stacked Long Short-Term Memory layers and a variational quantum layer. The latter employs a quantum feature map to embed input data into quantum states, which are then processed by a circuit ansatz. Finally, the expectation value of the circuit's outcome is taken over Pauli observables. Quantum properties such as superposition and entanglement are exploited to perform computations efficiently in a high-dimensional feature space. The proposed hybrid quantum-classical neural network is applied to a real-life challenging problem pertaining to the prediction of renewable energy time series. The comparison between the proposed approach and the classical counterpart shows that the former achieves better results in terms of prediction error, thus demonstrating better approximation of stochastic fluctuations and an overall effectiveness of the quantum variational approach also for prediction tasks.
Continuous Variable-based Quantum Computing (CVQC) has been developing at speed with a lot of promise in the field of quantum machine learning. It provides a direct and natural way to accommodate continuous values into the quantum computing framework. We carried out experiments on quantum simulators where we compared the results of time series forecasting on a type of continuous-variable quantum variational circuit, called CV-Quantum Neural Networks (CVQNN) for different types of time series like Energy Consumption data and stock price data. We compared their performance with a discrete variable-based variational quantum algorithm as well as with a classical Neural Network. Experiments showed that CVQNN can function just like a neural network but with a lesser number of parameters while tackling the two obstacles that are faced in qubit-based computing, which are, tackling continuous values and introducing controlled non-linearity into the circuits. We used the circuit for multi-step forecasting that performed better for a larger prediction window than one-step forecasting done iteratively on the predicted data. The resembling architecture of CVQNN with that of a neural network offers the flexibility of using a similar structure for both one-step and multi-step forecasting.