Time series forecasting with Qubit Neural Networks

Authors:
Carlos R. B. Azevedo;Tiago A. E. Ferreira
Affiliations:
Catholic University of Pernambuco, Brazil;Federal Rural University of Pernambuco, Brazil
Venue:
ASC '07 Proceedings of The Eleventh IASTED International Conference on Artificial Intelligence and Soft Computing
Year:
2007

Citing 6
Cited 1

Automatic early stopping using cross validation: quantifying the criteria

Neural Networks
Neural Networks Approach to the Random Walk Dilemma of Financial Time Series

Applied Intelligence
Orthogonality of decision boundaries in complex-valued neural networks

Neural Computation
A multilayered feed-forward network based on qubit neuron model

Systems and Computers in Japan
An Examination of Qubit Neural Network in Controlling an Inverted Pendulum

Neural Processing Letters
Algorithms for quantum computation: discrete logarithms and factoring

SFCS '94 Proceedings of the 35th Annual Symposium on Foundations of Computer Science

Multi-layer quantum neural network controller trained by real-coded genetic algorithm

Neurocomputing

Quantified Score

Hi-index	0.00

Visualization

Abstract

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.