Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Experiment Videos

Bi-directional computing architecture for time series prediction.

H Wakuya1, J M Zurada

  • 1Department of Electrical and Computer Engineering, University of Louisville, KY 40292, USA. wakuya@aivo.spd.louisville.edu

Neural Networks : the Official Journal of the International Neural Network Society
|November 23, 2001
PubMed
Summary
This summary is machine-generated.

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Neural networks and hybrid intelligent models: foundations, theory, and applications.

IEEE transactions on neural networks·2008
Same author

A dynamical system perspective of structural learning with forgetting.

IEEE transactions on neural networks·2008
Same author

Blind extraction of singularly mixed source signals.

IEEE transactions on neural networks·2008
Same author

Nonlinear blind source separation using a radial basis function network.

IEEE transactions on neural networks·2008
Same author

Extraction of rules from artificial neural networks for nonlinear regression.

IEEE transactions on neural networks·2008
Same author

A new design method for the complex-valued multistate Hopfield associative memory.

IEEE transactions on neural networks·2008
Same journal

Anchor-based disentanglement framework for incremental multi-view clustering.

Neural networks : the official journal of the International Neural Network Society·2026
Same journal

Complex-valued amplitude-phase interference modeling for adversarially robust classification.

Neural networks : the official journal of the International Neural Network Society·2026
Same journal

TraNce: Type-aware hypergraph neural network with biological mediators for drug repositioning.

Neural networks : the official journal of the International Neural Network Society·2026
Same journal

Decentralized ADMM for factorization-based Low-rank matrix estimation.

Neural networks : the official journal of the International Neural Network Society·2026
Same journal

Memristive neuromorphic circuit design inspired by the neural mechanisms of conditioned fear.

Neural networks : the official journal of the International Neural Network Society·2026
Same journal

Q-learning based asynchronous Boolean control networks stabilization with data loss.

Neural networks : the official journal of the International Neural Network Society·2026
See all related articles

This study introduces a novel bi-directional neural network for time series prediction, outperforming traditional uni-directional models. The bi-directional approach integrates future and past data for improved prediction accuracy.

Area of Science:

  • Artificial Intelligence
  • Machine Learning
  • Time Series Analysis

Background:

  • Traditional neural networks for time series prediction often use uni-directional computation.
  • Existing models face limitations in capturing complex temporal dependencies in time-variant data.

Purpose of the Study:

  • To propose and evaluate a novel bi-directional neural network architecture for time series prediction.
  • To investigate the integration of future and past information for enhanced predictive performance.

Main Methods:

  • Developed a bi-directional neural network model comprising two interconnected subnetworks.
  • Implemented mutual connections for complementary signal exchange between subnetworks.
  • Applied the model to both future and past prediction tasks.

Related Experiment Videos

Main Results:

  • The bi-directional model demonstrated superior performance compared to uni-directional methods.
  • Integration of future-past information significantly improved prediction scores.
  • The proposed architecture achieved better results on standard sunspots data.

Conclusions:

  • Bi-directional computation in neural networks offers a significant advantage for time series prediction.
  • The novel architecture effectively leverages complementary signals and future-past information integration.
  • This approach represents a promising advancement in predictive modeling for time-variant datasets.